├── README.md ├── matrix ├── README.md ├── ask_lm.py ├── language_models.py ├── matrix.py ├── requirements.txt ├── zs_blank_lm_responses │ ├── regular │ │ ├── welfare_battle.pkl │ │ ├── welfare_chicken.pkl │ │ ├── welfare_prisoners.pkl │ │ └── welfare_stag.pkl │ └── scrambled │ │ ├── welfare_battle.pkl │ │ ├── welfare_chicken.pkl │ │ ├── welfare_prisoners.pkl │ │ └── welfare_stag.pkl ├── zs_lm_responses │ ├── regular │ │ ├── equality_battle.pkl │ │ ├── equality_chicken.pkl │ │ ├── equality_prisoners.pkl │ │ ├── equality_stag.pkl │ │ ├── pareto_battle.pkl │ │ ├── pareto_chicken.pkl │ │ ├── pareto_prisoners.pkl │ │ ├── pareto_stag.pkl │ │ ├── rawlsian_battle.pkl │ │ ├── rawlsian_chicken.pkl │ │ ├── rawlsian_prisoners.pkl │ │ ├── rawlsian_stag.pkl │ │ ├── welfare_battle.pkl │ │ ├── welfare_chicken.pkl │ │ ├── welfare_prisoners.pkl │ │ └── welfare_stag.pkl │ └── scrambled │ │ ├── equality_battle.pkl │ │ ├── equality_chicken.pkl │ │ ├── equality_prisoners.pkl │ │ ├── equality_stag.pkl │ │ ├── pareto_battle.pkl │ │ ├── pareto_chicken.pkl │ │ ├── pareto_prisoners.pkl │ │ ├── pareto_stag.pkl │ │ ├── rawlsian_battle.pkl │ │ ├── rawlsian_chicken.pkl │ │ ├── rawlsian_prisoners.pkl │ │ ├── rawlsian_stag.pkl │ │ ├── welfare_battle.pkl │ │ ├── welfare_chicken.pkl │ │ ├── welfare_prisoners.pkl │ │ └── welfare_stag.pkl └── zs_matrix_prompts.py ├── negotiation ├── README.md ├── base_prompts.py ├── coarse_dialogue_acts │ ├── __init__.py │ ├── __pycache__ │ │ ├── __init__.cpython-38.pyc │ │ ├── __init__.cpython-39.pyc │ │ ├── agent.cpython-38.pyc │ │ ├── corpus.cpython-38.pyc │ │ ├── corpus.cpython-39.pyc │ │ ├── dialogue_state.cpython-38.pyc │ │ ├── dictionary.cpython-38.pyc │ │ ├── entity.cpython-38.pyc │ │ ├── kb.cpython-38.pyc │ │ ├── lexicon.cpython-38.pyc │ │ ├── lf.cpython-38.pyc │ │ ├── parser.cpython-38.pyc │ │ └── utterance.cpython-38.pyc │ ├── agent.py │ ├── corpus.py │ ├── dialogue_state.py │ ├── dictionary.py │ ├── entity.py │ ├── kb.py │ ├── lexicon.py │ ├── lf.py │ ├── parser.py │ ├── utils.py │ └── utterance.py ├── data.py ├── data │ ├── data.txt │ ├── selfplay.txt │ ├── selfplay_lite.txt │ ├── test.txt │ ├── test_contexts.txt │ ├── train.txt │ ├── train_contexts.txt │ ├── train_lite_contexts.txt │ ├── val.txt │ └── val_contexts.txt ├── eval.py ├── ground_truth_rewards.py ├── language_models.py ├── models │ ├── __init__.py │ ├── __pycache__ │ │ ├── __init__.cpython-38.pyc │ │ ├── cda_rnn_model.cpython-38.pyc │ │ ├── dialog_model.cpython-38.pyc │ │ ├── modules.cpython-38.pyc │ │ ├── partner_aware_model.cpython-38.pyc │ │ └── partner_prediction_model.cpython-38.pyc │ ├── cda_rnn_model.py │ ├── dialog_model.py │ └── modules.py ├── reinforce.py ├── requirements.txt ├── reward_model_accuracy.py ├── selfplay.py ├── sl.py ├── sl_baseline.py └── utils │ ├── __pycache__ │ ├── agent.cpython-38.pyc │ ├── data.cpython-38.pyc │ ├── dialog.cpython-38.pyc │ ├── domain.cpython-38.pyc │ ├── engine.cpython-38.pyc │ ├── metric.cpython-38.pyc │ ├── rewards.cpython-38.pyc │ ├── trainer.cpython-38.pyc │ ├── utils.cpython-38.pyc │ └── utils.cpython-39.pyc │ ├── agent.py │ ├── data.py │ ├── dialog.py │ ├── domain.py │ ├── engine.py │ ├── metric.py │ ├── rewards.py │ ├── trainer.py │ └── utils.py └── ultimatum ├── README.md ├── ask_lm.py ├── generate_data.py ├── inequity_aversion_None.pkl ├── language_models.py ├── lm_responses ├── inequity_aversion_None.pkl ├── inequity_aversion_None_train.pkl ├── low_high_payoff_10.pkl ├── low_high_payoff_100.pkl ├── low_high_payoff_100_train.pkl ├── low_high_payoff_10_train.pkl ├── low_high_percentage_0.3.pkl ├── low_high_percentage_0.3_train.pkl ├── low_high_percentage_0.6.pkl └── low_high_percentage_0.6_train.pkl ├── lm_responses_shorter ├── inequity_aversion_None.pkl ├── inequity_aversion_None_train.pkl ├── low_high_payoff_10.pkl ├── low_high_payoff_100.pkl ├── low_high_payoff_100_train.pkl ├── low_high_payoff_10_train.pkl ├── low_high_percentage_0.3.pkl ├── low_high_percentage_0.3_train.pkl ├── low_high_percentage_0.6.pkl └── low_high_percentage_0.6_train.pkl ├── low_high_payoff_10.pkl ├── low_high_payoff_100.pkl ├── low_high_percentage_0.3.pkl ├── low_high_percentage_0.6.pkl ├── requirements.txt ├── sl.ipynb ├── sl_responses ├── inequity_aversion_None_train.pkl ├── low_high_payoff_100_train.pkl ├── low_high_payoff_10_train.pkl ├── low_high_percentage_0.3_train.pkl └── low_high_percentage_0.6_train.pkl ├── sl_responses_shorter ├── inequity_aversion_None_train.pkl ├── low_high_payoff_100_train.pkl ├── low_high_payoff_10_train.pkl ├── low_high_percentage_0.3_train.pkl └── low_high_percentage_0.6_train.pkl ├── sl_shorter.ipynb ├── train_configs.py ├── ultimatum.py └── ultimatum_prompts.py /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/README.md -------------------------------------------------------------------------------- /matrix/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/matrix/README.md -------------------------------------------------------------------------------- /matrix/ask_lm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/matrix/ask_lm.py -------------------------------------------------------------------------------- /matrix/language_models.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/matrix/language_models.py -------------------------------------------------------------------------------- /matrix/matrix.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/matrix/matrix.py -------------------------------------------------------------------------------- /matrix/requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/matrix/requirements.txt -------------------------------------------------------------------------------- /matrix/zs_blank_lm_responses/regular/welfare_battle.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/matrix/zs_blank_lm_responses/regular/welfare_battle.pkl -------------------------------------------------------------------------------- /matrix/zs_blank_lm_responses/regular/welfare_chicken.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/matrix/zs_blank_lm_responses/regular/welfare_chicken.pkl -------------------------------------------------------------------------------- /matrix/zs_blank_lm_responses/regular/welfare_prisoners.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/matrix/zs_blank_lm_responses/regular/welfare_prisoners.pkl -------------------------------------------------------------------------------- /matrix/zs_blank_lm_responses/regular/welfare_stag.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/matrix/zs_blank_lm_responses/regular/welfare_stag.pkl -------------------------------------------------------------------------------- /matrix/zs_blank_lm_responses/scrambled/welfare_battle.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/matrix/zs_blank_lm_responses/scrambled/welfare_battle.pkl -------------------------------------------------------------------------------- /matrix/zs_blank_lm_responses/scrambled/welfare_chicken.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/matrix/zs_blank_lm_responses/scrambled/welfare_chicken.pkl -------------------------------------------------------------------------------- /matrix/zs_blank_lm_responses/scrambled/welfare_prisoners.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/matrix/zs_blank_lm_responses/scrambled/welfare_prisoners.pkl -------------------------------------------------------------------------------- /matrix/zs_blank_lm_responses/scrambled/welfare_stag.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/matrix/zs_blank_lm_responses/scrambled/welfare_stag.pkl -------------------------------------------------------------------------------- /matrix/zs_lm_responses/regular/equality_battle.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/matrix/zs_lm_responses/regular/equality_battle.pkl -------------------------------------------------------------------------------- /matrix/zs_lm_responses/regular/equality_chicken.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/matrix/zs_lm_responses/regular/equality_chicken.pkl -------------------------------------------------------------------------------- /matrix/zs_lm_responses/regular/equality_prisoners.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/matrix/zs_lm_responses/regular/equality_prisoners.pkl -------------------------------------------------------------------------------- /matrix/zs_lm_responses/regular/equality_stag.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/matrix/zs_lm_responses/regular/equality_stag.pkl -------------------------------------------------------------------------------- /matrix/zs_lm_responses/regular/pareto_battle.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/matrix/zs_lm_responses/regular/pareto_battle.pkl -------------------------------------------------------------------------------- /matrix/zs_lm_responses/regular/pareto_chicken.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/matrix/zs_lm_responses/regular/pareto_chicken.pkl -------------------------------------------------------------------------------- /matrix/zs_lm_responses/regular/pareto_prisoners.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/matrix/zs_lm_responses/regular/pareto_prisoners.pkl -------------------------------------------------------------------------------- /matrix/zs_lm_responses/regular/pareto_stag.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/matrix/zs_lm_responses/regular/pareto_stag.pkl -------------------------------------------------------------------------------- /matrix/zs_lm_responses/regular/rawlsian_battle.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/matrix/zs_lm_responses/regular/rawlsian_battle.pkl -------------------------------------------------------------------------------- /matrix/zs_lm_responses/regular/rawlsian_chicken.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/matrix/zs_lm_responses/regular/rawlsian_chicken.pkl -------------------------------------------------------------------------------- /matrix/zs_lm_responses/regular/rawlsian_prisoners.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/matrix/zs_lm_responses/regular/rawlsian_prisoners.pkl -------------------------------------------------------------------------------- /matrix/zs_lm_responses/regular/rawlsian_stag.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/matrix/zs_lm_responses/regular/rawlsian_stag.pkl -------------------------------------------------------------------------------- /matrix/zs_lm_responses/regular/welfare_battle.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/matrix/zs_lm_responses/regular/welfare_battle.pkl -------------------------------------------------------------------------------- /matrix/zs_lm_responses/regular/welfare_chicken.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/matrix/zs_lm_responses/regular/welfare_chicken.pkl -------------------------------------------------------------------------------- /matrix/zs_lm_responses/regular/welfare_prisoners.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/matrix/zs_lm_responses/regular/welfare_prisoners.pkl -------------------------------------------------------------------------------- /matrix/zs_lm_responses/regular/welfare_stag.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/matrix/zs_lm_responses/regular/welfare_stag.pkl -------------------------------------------------------------------------------- /matrix/zs_lm_responses/scrambled/equality_battle.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/matrix/zs_lm_responses/scrambled/equality_battle.pkl -------------------------------------------------------------------------------- /matrix/zs_lm_responses/scrambled/equality_chicken.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/matrix/zs_lm_responses/scrambled/equality_chicken.pkl -------------------------------------------------------------------------------- /matrix/zs_lm_responses/scrambled/equality_prisoners.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/matrix/zs_lm_responses/scrambled/equality_prisoners.pkl -------------------------------------------------------------------------------- /matrix/zs_lm_responses/scrambled/equality_stag.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/matrix/zs_lm_responses/scrambled/equality_stag.pkl -------------------------------------------------------------------------------- /matrix/zs_lm_responses/scrambled/pareto_battle.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/matrix/zs_lm_responses/scrambled/pareto_battle.pkl -------------------------------------------------------------------------------- /matrix/zs_lm_responses/scrambled/pareto_chicken.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/matrix/zs_lm_responses/scrambled/pareto_chicken.pkl -------------------------------------------------------------------------------- /matrix/zs_lm_responses/scrambled/pareto_prisoners.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/matrix/zs_lm_responses/scrambled/pareto_prisoners.pkl -------------------------------------------------------------------------------- /matrix/zs_lm_responses/scrambled/pareto_stag.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/matrix/zs_lm_responses/scrambled/pareto_stag.pkl -------------------------------------------------------------------------------- /matrix/zs_lm_responses/scrambled/rawlsian_battle.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/matrix/zs_lm_responses/scrambled/rawlsian_battle.pkl -------------------------------------------------------------------------------- /matrix/zs_lm_responses/scrambled/rawlsian_chicken.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/matrix/zs_lm_responses/scrambled/rawlsian_chicken.pkl -------------------------------------------------------------------------------- /matrix/zs_lm_responses/scrambled/rawlsian_prisoners.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/matrix/zs_lm_responses/scrambled/rawlsian_prisoners.pkl -------------------------------------------------------------------------------- /matrix/zs_lm_responses/scrambled/rawlsian_stag.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/matrix/zs_lm_responses/scrambled/rawlsian_stag.pkl -------------------------------------------------------------------------------- /matrix/zs_lm_responses/scrambled/welfare_battle.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/matrix/zs_lm_responses/scrambled/welfare_battle.pkl -------------------------------------------------------------------------------- /matrix/zs_lm_responses/scrambled/welfare_chicken.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/matrix/zs_lm_responses/scrambled/welfare_chicken.pkl -------------------------------------------------------------------------------- /matrix/zs_lm_responses/scrambled/welfare_prisoners.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/matrix/zs_lm_responses/scrambled/welfare_prisoners.pkl -------------------------------------------------------------------------------- /matrix/zs_lm_responses/scrambled/welfare_stag.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/matrix/zs_lm_responses/scrambled/welfare_stag.pkl -------------------------------------------------------------------------------- /matrix/zs_matrix_prompts.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/matrix/zs_matrix_prompts.py -------------------------------------------------------------------------------- /negotiation/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/negotiation/README.md -------------------------------------------------------------------------------- /negotiation/base_prompts.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/negotiation/base_prompts.py -------------------------------------------------------------------------------- /negotiation/coarse_dialogue_acts/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /negotiation/coarse_dialogue_acts/__pycache__/__init__.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/negotiation/coarse_dialogue_acts/__pycache__/__init__.cpython-38.pyc -------------------------------------------------------------------------------- /negotiation/coarse_dialogue_acts/__pycache__/__init__.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/negotiation/coarse_dialogue_acts/__pycache__/__init__.cpython-39.pyc -------------------------------------------------------------------------------- /negotiation/coarse_dialogue_acts/__pycache__/agent.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/negotiation/coarse_dialogue_acts/__pycache__/agent.cpython-38.pyc -------------------------------------------------------------------------------- /negotiation/coarse_dialogue_acts/__pycache__/corpus.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/negotiation/coarse_dialogue_acts/__pycache__/corpus.cpython-38.pyc -------------------------------------------------------------------------------- /negotiation/coarse_dialogue_acts/__pycache__/corpus.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/negotiation/coarse_dialogue_acts/__pycache__/corpus.cpython-39.pyc -------------------------------------------------------------------------------- /negotiation/coarse_dialogue_acts/__pycache__/dialogue_state.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/negotiation/coarse_dialogue_acts/__pycache__/dialogue_state.cpython-38.pyc -------------------------------------------------------------------------------- /negotiation/coarse_dialogue_acts/__pycache__/dictionary.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/negotiation/coarse_dialogue_acts/__pycache__/dictionary.cpython-38.pyc -------------------------------------------------------------------------------- /negotiation/coarse_dialogue_acts/__pycache__/entity.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/negotiation/coarse_dialogue_acts/__pycache__/entity.cpython-38.pyc -------------------------------------------------------------------------------- /negotiation/coarse_dialogue_acts/__pycache__/kb.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/negotiation/coarse_dialogue_acts/__pycache__/kb.cpython-38.pyc -------------------------------------------------------------------------------- /negotiation/coarse_dialogue_acts/__pycache__/lexicon.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/negotiation/coarse_dialogue_acts/__pycache__/lexicon.cpython-38.pyc -------------------------------------------------------------------------------- /negotiation/coarse_dialogue_acts/__pycache__/lf.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/negotiation/coarse_dialogue_acts/__pycache__/lf.cpython-38.pyc -------------------------------------------------------------------------------- /negotiation/coarse_dialogue_acts/__pycache__/parser.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/negotiation/coarse_dialogue_acts/__pycache__/parser.cpython-38.pyc -------------------------------------------------------------------------------- /negotiation/coarse_dialogue_acts/__pycache__/utterance.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/negotiation/coarse_dialogue_acts/__pycache__/utterance.cpython-38.pyc -------------------------------------------------------------------------------- /negotiation/coarse_dialogue_acts/agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/negotiation/coarse_dialogue_acts/agent.py -------------------------------------------------------------------------------- /negotiation/coarse_dialogue_acts/corpus.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/negotiation/coarse_dialogue_acts/corpus.py -------------------------------------------------------------------------------- /negotiation/coarse_dialogue_acts/dialogue_state.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/negotiation/coarse_dialogue_acts/dialogue_state.py -------------------------------------------------------------------------------- /negotiation/coarse_dialogue_acts/dictionary.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/negotiation/coarse_dialogue_acts/dictionary.py -------------------------------------------------------------------------------- /negotiation/coarse_dialogue_acts/entity.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/negotiation/coarse_dialogue_acts/entity.py -------------------------------------------------------------------------------- /negotiation/coarse_dialogue_acts/kb.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/negotiation/coarse_dialogue_acts/kb.py -------------------------------------------------------------------------------- /negotiation/coarse_dialogue_acts/lexicon.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/negotiation/coarse_dialogue_acts/lexicon.py -------------------------------------------------------------------------------- /negotiation/coarse_dialogue_acts/lf.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/negotiation/coarse_dialogue_acts/lf.py -------------------------------------------------------------------------------- /negotiation/coarse_dialogue_acts/parser.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/negotiation/coarse_dialogue_acts/parser.py -------------------------------------------------------------------------------- /negotiation/coarse_dialogue_acts/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/negotiation/coarse_dialogue_acts/utils.py -------------------------------------------------------------------------------- /negotiation/coarse_dialogue_acts/utterance.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/negotiation/coarse_dialogue_acts/utterance.py -------------------------------------------------------------------------------- /negotiation/data.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/negotiation/data.py -------------------------------------------------------------------------------- /negotiation/data/data.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/negotiation/data/data.txt -------------------------------------------------------------------------------- /negotiation/data/selfplay.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/negotiation/data/selfplay.txt -------------------------------------------------------------------------------- /negotiation/data/selfplay_lite.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/negotiation/data/selfplay_lite.txt -------------------------------------------------------------------------------- /negotiation/data/test.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/negotiation/data/test.txt -------------------------------------------------------------------------------- /negotiation/data/test_contexts.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/negotiation/data/test_contexts.txt -------------------------------------------------------------------------------- /negotiation/data/train.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/negotiation/data/train.txt -------------------------------------------------------------------------------- /negotiation/data/train_contexts.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/negotiation/data/train_contexts.txt -------------------------------------------------------------------------------- /negotiation/data/train_lite_contexts.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/negotiation/data/train_lite_contexts.txt -------------------------------------------------------------------------------- /negotiation/data/val.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/negotiation/data/val.txt -------------------------------------------------------------------------------- /negotiation/data/val_contexts.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/negotiation/data/val_contexts.txt -------------------------------------------------------------------------------- /negotiation/eval.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/negotiation/eval.py -------------------------------------------------------------------------------- /negotiation/ground_truth_rewards.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/negotiation/ground_truth_rewards.py -------------------------------------------------------------------------------- /negotiation/language_models.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/negotiation/language_models.py -------------------------------------------------------------------------------- /negotiation/models/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/negotiation/models/__init__.py -------------------------------------------------------------------------------- /negotiation/models/__pycache__/__init__.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/negotiation/models/__pycache__/__init__.cpython-38.pyc -------------------------------------------------------------------------------- /negotiation/models/__pycache__/cda_rnn_model.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/negotiation/models/__pycache__/cda_rnn_model.cpython-38.pyc -------------------------------------------------------------------------------- /negotiation/models/__pycache__/dialog_model.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/negotiation/models/__pycache__/dialog_model.cpython-38.pyc -------------------------------------------------------------------------------- /negotiation/models/__pycache__/modules.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/negotiation/models/__pycache__/modules.cpython-38.pyc -------------------------------------------------------------------------------- /negotiation/models/__pycache__/partner_aware_model.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/negotiation/models/__pycache__/partner_aware_model.cpython-38.pyc -------------------------------------------------------------------------------- /negotiation/models/__pycache__/partner_prediction_model.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/negotiation/models/__pycache__/partner_prediction_model.cpython-38.pyc -------------------------------------------------------------------------------- /negotiation/models/cda_rnn_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/negotiation/models/cda_rnn_model.py -------------------------------------------------------------------------------- /negotiation/models/dialog_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/negotiation/models/dialog_model.py -------------------------------------------------------------------------------- /negotiation/models/modules.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/negotiation/models/modules.py -------------------------------------------------------------------------------- /negotiation/reinforce.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/negotiation/reinforce.py -------------------------------------------------------------------------------- /negotiation/requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/negotiation/requirements.txt -------------------------------------------------------------------------------- /negotiation/reward_model_accuracy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/negotiation/reward_model_accuracy.py -------------------------------------------------------------------------------- /negotiation/selfplay.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/negotiation/selfplay.py -------------------------------------------------------------------------------- /negotiation/sl.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/negotiation/sl.py -------------------------------------------------------------------------------- /negotiation/sl_baseline.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/negotiation/sl_baseline.py -------------------------------------------------------------------------------- /negotiation/utils/__pycache__/agent.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/negotiation/utils/__pycache__/agent.cpython-38.pyc -------------------------------------------------------------------------------- /negotiation/utils/__pycache__/data.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/negotiation/utils/__pycache__/data.cpython-38.pyc -------------------------------------------------------------------------------- /negotiation/utils/__pycache__/dialog.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/negotiation/utils/__pycache__/dialog.cpython-38.pyc -------------------------------------------------------------------------------- /negotiation/utils/__pycache__/domain.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/negotiation/utils/__pycache__/domain.cpython-38.pyc -------------------------------------------------------------------------------- /negotiation/utils/__pycache__/engine.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/negotiation/utils/__pycache__/engine.cpython-38.pyc -------------------------------------------------------------------------------- /negotiation/utils/__pycache__/metric.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/negotiation/utils/__pycache__/metric.cpython-38.pyc -------------------------------------------------------------------------------- /negotiation/utils/__pycache__/rewards.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/negotiation/utils/__pycache__/rewards.cpython-38.pyc -------------------------------------------------------------------------------- /negotiation/utils/__pycache__/trainer.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/negotiation/utils/__pycache__/trainer.cpython-38.pyc -------------------------------------------------------------------------------- /negotiation/utils/__pycache__/utils.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/negotiation/utils/__pycache__/utils.cpython-38.pyc -------------------------------------------------------------------------------- /negotiation/utils/__pycache__/utils.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/negotiation/utils/__pycache__/utils.cpython-39.pyc -------------------------------------------------------------------------------- /negotiation/utils/agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/negotiation/utils/agent.py -------------------------------------------------------------------------------- /negotiation/utils/data.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/negotiation/utils/data.py -------------------------------------------------------------------------------- /negotiation/utils/dialog.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/negotiation/utils/dialog.py -------------------------------------------------------------------------------- /negotiation/utils/domain.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/negotiation/utils/domain.py -------------------------------------------------------------------------------- /negotiation/utils/engine.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/negotiation/utils/engine.py -------------------------------------------------------------------------------- /negotiation/utils/metric.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/negotiation/utils/metric.py -------------------------------------------------------------------------------- /negotiation/utils/rewards.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/negotiation/utils/rewards.py -------------------------------------------------------------------------------- /negotiation/utils/trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/negotiation/utils/trainer.py -------------------------------------------------------------------------------- /negotiation/utils/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/negotiation/utils/utils.py -------------------------------------------------------------------------------- /ultimatum/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/ultimatum/README.md -------------------------------------------------------------------------------- /ultimatum/ask_lm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/ultimatum/ask_lm.py -------------------------------------------------------------------------------- /ultimatum/generate_data.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/ultimatum/generate_data.py -------------------------------------------------------------------------------- /ultimatum/inequity_aversion_None.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/ultimatum/inequity_aversion_None.pkl -------------------------------------------------------------------------------- /ultimatum/language_models.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/ultimatum/language_models.py -------------------------------------------------------------------------------- /ultimatum/lm_responses/inequity_aversion_None.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/ultimatum/lm_responses/inequity_aversion_None.pkl -------------------------------------------------------------------------------- /ultimatum/lm_responses/inequity_aversion_None_train.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/ultimatum/lm_responses/inequity_aversion_None_train.pkl -------------------------------------------------------------------------------- /ultimatum/lm_responses/low_high_payoff_10.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/ultimatum/lm_responses/low_high_payoff_10.pkl -------------------------------------------------------------------------------- /ultimatum/lm_responses/low_high_payoff_100.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/ultimatum/lm_responses/low_high_payoff_100.pkl -------------------------------------------------------------------------------- /ultimatum/lm_responses/low_high_payoff_100_train.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/ultimatum/lm_responses/low_high_payoff_100_train.pkl -------------------------------------------------------------------------------- /ultimatum/lm_responses/low_high_payoff_10_train.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/ultimatum/lm_responses/low_high_payoff_10_train.pkl -------------------------------------------------------------------------------- /ultimatum/lm_responses/low_high_percentage_0.3.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/ultimatum/lm_responses/low_high_percentage_0.3.pkl -------------------------------------------------------------------------------- /ultimatum/lm_responses/low_high_percentage_0.3_train.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/ultimatum/lm_responses/low_high_percentage_0.3_train.pkl -------------------------------------------------------------------------------- /ultimatum/lm_responses/low_high_percentage_0.6.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/ultimatum/lm_responses/low_high_percentage_0.6.pkl -------------------------------------------------------------------------------- /ultimatum/lm_responses/low_high_percentage_0.6_train.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/ultimatum/lm_responses/low_high_percentage_0.6_train.pkl -------------------------------------------------------------------------------- /ultimatum/lm_responses_shorter/inequity_aversion_None.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/ultimatum/lm_responses_shorter/inequity_aversion_None.pkl -------------------------------------------------------------------------------- /ultimatum/lm_responses_shorter/inequity_aversion_None_train.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/ultimatum/lm_responses_shorter/inequity_aversion_None_train.pkl -------------------------------------------------------------------------------- /ultimatum/lm_responses_shorter/low_high_payoff_10.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/ultimatum/lm_responses_shorter/low_high_payoff_10.pkl -------------------------------------------------------------------------------- /ultimatum/lm_responses_shorter/low_high_payoff_100.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/ultimatum/lm_responses_shorter/low_high_payoff_100.pkl -------------------------------------------------------------------------------- /ultimatum/lm_responses_shorter/low_high_payoff_100_train.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/ultimatum/lm_responses_shorter/low_high_payoff_100_train.pkl -------------------------------------------------------------------------------- /ultimatum/lm_responses_shorter/low_high_payoff_10_train.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/ultimatum/lm_responses_shorter/low_high_payoff_10_train.pkl -------------------------------------------------------------------------------- /ultimatum/lm_responses_shorter/low_high_percentage_0.3.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/ultimatum/lm_responses_shorter/low_high_percentage_0.3.pkl -------------------------------------------------------------------------------- /ultimatum/lm_responses_shorter/low_high_percentage_0.3_train.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/ultimatum/lm_responses_shorter/low_high_percentage_0.3_train.pkl -------------------------------------------------------------------------------- /ultimatum/lm_responses_shorter/low_high_percentage_0.6.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/ultimatum/lm_responses_shorter/low_high_percentage_0.6.pkl -------------------------------------------------------------------------------- /ultimatum/lm_responses_shorter/low_high_percentage_0.6_train.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/ultimatum/lm_responses_shorter/low_high_percentage_0.6_train.pkl -------------------------------------------------------------------------------- /ultimatum/low_high_payoff_10.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/ultimatum/low_high_payoff_10.pkl -------------------------------------------------------------------------------- /ultimatum/low_high_payoff_100.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/ultimatum/low_high_payoff_100.pkl -------------------------------------------------------------------------------- /ultimatum/low_high_percentage_0.3.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/ultimatum/low_high_percentage_0.3.pkl -------------------------------------------------------------------------------- /ultimatum/low_high_percentage_0.6.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/ultimatum/low_high_percentage_0.6.pkl -------------------------------------------------------------------------------- /ultimatum/requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/ultimatum/requirements.txt -------------------------------------------------------------------------------- /ultimatum/sl.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/ultimatum/sl.ipynb -------------------------------------------------------------------------------- /ultimatum/sl_responses/inequity_aversion_None_train.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/ultimatum/sl_responses/inequity_aversion_None_train.pkl -------------------------------------------------------------------------------- /ultimatum/sl_responses/low_high_payoff_100_train.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/ultimatum/sl_responses/low_high_payoff_100_train.pkl -------------------------------------------------------------------------------- /ultimatum/sl_responses/low_high_payoff_10_train.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/ultimatum/sl_responses/low_high_payoff_10_train.pkl -------------------------------------------------------------------------------- /ultimatum/sl_responses/low_high_percentage_0.3_train.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/ultimatum/sl_responses/low_high_percentage_0.3_train.pkl -------------------------------------------------------------------------------- /ultimatum/sl_responses/low_high_percentage_0.6_train.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/ultimatum/sl_responses/low_high_percentage_0.6_train.pkl -------------------------------------------------------------------------------- /ultimatum/sl_responses_shorter/inequity_aversion_None_train.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/ultimatum/sl_responses_shorter/inequity_aversion_None_train.pkl -------------------------------------------------------------------------------- /ultimatum/sl_responses_shorter/low_high_payoff_100_train.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/ultimatum/sl_responses_shorter/low_high_payoff_100_train.pkl -------------------------------------------------------------------------------- /ultimatum/sl_responses_shorter/low_high_payoff_10_train.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/ultimatum/sl_responses_shorter/low_high_payoff_10_train.pkl -------------------------------------------------------------------------------- /ultimatum/sl_responses_shorter/low_high_percentage_0.3_train.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/ultimatum/sl_responses_shorter/low_high_percentage_0.3_train.pkl -------------------------------------------------------------------------------- /ultimatum/sl_responses_shorter/low_high_percentage_0.6_train.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/ultimatum/sl_responses_shorter/low_high_percentage_0.6_train.pkl -------------------------------------------------------------------------------- /ultimatum/sl_shorter.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/ultimatum/sl_shorter.ipynb -------------------------------------------------------------------------------- /ultimatum/train_configs.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/ultimatum/train_configs.py -------------------------------------------------------------------------------- /ultimatum/ultimatum.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/ultimatum/ultimatum.py -------------------------------------------------------------------------------- /ultimatum/ultimatum_prompts.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/minaek/reward_design_with_llms/HEAD/ultimatum/ultimatum_prompts.py --------------------------------------------------------------------------------