├── .gitignore ├── 156_supplement.pdf ├── CODE_OF_CONDUCT.md ├── CONTRIBUTING.md ├── LICENSE ├── README.md ├── local_mnf_toy_regression.png ├── qlearn ├── atari │ ├── bayes_backprop_agent.py │ ├── bootstrapped_agent.py │ ├── dqn_agent.py │ ├── local_mnf_agent.py │ ├── mnf_agent.py │ ├── noisy_agent.py │ ├── prior_bootstrapped_agent.py │ ├── train_bayes_backprop_agent.py │ ├── train_bootstrapped_agent.py │ ├── train_dqn.py │ ├── train_mnf_agent.py │ ├── train_noisy_agent.py │ └── train_prior_bootstrapped_agent.py ├── commun │ ├── bayes_backprop_layer.py │ ├── dropout_toy_regression.py │ ├── local_mnf_layer.py │ ├── local_mnf_toy_regression.py │ ├── mnf_layer.py │ ├── mnf_toy_regression.py │ ├── noisy_layer.py │ ├── norm_flows.py │ ├── toy_regression.py │ ├── utils.py │ └── variational_dropout_layer.py ├── envs │ └── nchain.py └── toys │ ├── agent.py │ ├── bayes_backprop_agent.py │ ├── bootstrapped_agent.py │ ├── main_nchain.py │ ├── mnf_agent.py │ ├── model.py │ ├── noisy_agent.py │ └── test.py └── setup.py /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/facebookresearch/RandomizedValueFunctions/HEAD/.gitignore -------------------------------------------------------------------------------- /156_supplement.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/facebookresearch/RandomizedValueFunctions/HEAD/156_supplement.pdf -------------------------------------------------------------------------------- /CODE_OF_CONDUCT.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/facebookresearch/RandomizedValueFunctions/HEAD/CODE_OF_CONDUCT.md -------------------------------------------------------------------------------- /CONTRIBUTING.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/facebookresearch/RandomizedValueFunctions/HEAD/CONTRIBUTING.md -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/facebookresearch/RandomizedValueFunctions/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/facebookresearch/RandomizedValueFunctions/HEAD/README.md -------------------------------------------------------------------------------- /local_mnf_toy_regression.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/facebookresearch/RandomizedValueFunctions/HEAD/local_mnf_toy_regression.png -------------------------------------------------------------------------------- /qlearn/atari/bayes_backprop_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/facebookresearch/RandomizedValueFunctions/HEAD/qlearn/atari/bayes_backprop_agent.py -------------------------------------------------------------------------------- /qlearn/atari/bootstrapped_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/facebookresearch/RandomizedValueFunctions/HEAD/qlearn/atari/bootstrapped_agent.py -------------------------------------------------------------------------------- /qlearn/atari/dqn_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/facebookresearch/RandomizedValueFunctions/HEAD/qlearn/atari/dqn_agent.py -------------------------------------------------------------------------------- /qlearn/atari/local_mnf_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/facebookresearch/RandomizedValueFunctions/HEAD/qlearn/atari/local_mnf_agent.py -------------------------------------------------------------------------------- /qlearn/atari/mnf_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/facebookresearch/RandomizedValueFunctions/HEAD/qlearn/atari/mnf_agent.py -------------------------------------------------------------------------------- /qlearn/atari/noisy_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/facebookresearch/RandomizedValueFunctions/HEAD/qlearn/atari/noisy_agent.py -------------------------------------------------------------------------------- /qlearn/atari/prior_bootstrapped_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/facebookresearch/RandomizedValueFunctions/HEAD/qlearn/atari/prior_bootstrapped_agent.py -------------------------------------------------------------------------------- /qlearn/atari/train_bayes_backprop_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/facebookresearch/RandomizedValueFunctions/HEAD/qlearn/atari/train_bayes_backprop_agent.py -------------------------------------------------------------------------------- /qlearn/atari/train_bootstrapped_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/facebookresearch/RandomizedValueFunctions/HEAD/qlearn/atari/train_bootstrapped_agent.py -------------------------------------------------------------------------------- /qlearn/atari/train_dqn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/facebookresearch/RandomizedValueFunctions/HEAD/qlearn/atari/train_dqn.py -------------------------------------------------------------------------------- /qlearn/atari/train_mnf_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/facebookresearch/RandomizedValueFunctions/HEAD/qlearn/atari/train_mnf_agent.py -------------------------------------------------------------------------------- /qlearn/atari/train_noisy_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/facebookresearch/RandomizedValueFunctions/HEAD/qlearn/atari/train_noisy_agent.py -------------------------------------------------------------------------------- /qlearn/atari/train_prior_bootstrapped_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/facebookresearch/RandomizedValueFunctions/HEAD/qlearn/atari/train_prior_bootstrapped_agent.py -------------------------------------------------------------------------------- /qlearn/commun/bayes_backprop_layer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/facebookresearch/RandomizedValueFunctions/HEAD/qlearn/commun/bayes_backprop_layer.py -------------------------------------------------------------------------------- /qlearn/commun/dropout_toy_regression.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/facebookresearch/RandomizedValueFunctions/HEAD/qlearn/commun/dropout_toy_regression.py -------------------------------------------------------------------------------- /qlearn/commun/local_mnf_layer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/facebookresearch/RandomizedValueFunctions/HEAD/qlearn/commun/local_mnf_layer.py -------------------------------------------------------------------------------- /qlearn/commun/local_mnf_toy_regression.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/facebookresearch/RandomizedValueFunctions/HEAD/qlearn/commun/local_mnf_toy_regression.py -------------------------------------------------------------------------------- /qlearn/commun/mnf_layer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/facebookresearch/RandomizedValueFunctions/HEAD/qlearn/commun/mnf_layer.py -------------------------------------------------------------------------------- /qlearn/commun/mnf_toy_regression.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/facebookresearch/RandomizedValueFunctions/HEAD/qlearn/commun/mnf_toy_regression.py -------------------------------------------------------------------------------- /qlearn/commun/noisy_layer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/facebookresearch/RandomizedValueFunctions/HEAD/qlearn/commun/noisy_layer.py -------------------------------------------------------------------------------- /qlearn/commun/norm_flows.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/facebookresearch/RandomizedValueFunctions/HEAD/qlearn/commun/norm_flows.py -------------------------------------------------------------------------------- /qlearn/commun/toy_regression.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/facebookresearch/RandomizedValueFunctions/HEAD/qlearn/commun/toy_regression.py -------------------------------------------------------------------------------- /qlearn/commun/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/facebookresearch/RandomizedValueFunctions/HEAD/qlearn/commun/utils.py -------------------------------------------------------------------------------- /qlearn/commun/variational_dropout_layer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/facebookresearch/RandomizedValueFunctions/HEAD/qlearn/commun/variational_dropout_layer.py -------------------------------------------------------------------------------- /qlearn/envs/nchain.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/facebookresearch/RandomizedValueFunctions/HEAD/qlearn/envs/nchain.py -------------------------------------------------------------------------------- /qlearn/toys/agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/facebookresearch/RandomizedValueFunctions/HEAD/qlearn/toys/agent.py -------------------------------------------------------------------------------- /qlearn/toys/bayes_backprop_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/facebookresearch/RandomizedValueFunctions/HEAD/qlearn/toys/bayes_backprop_agent.py -------------------------------------------------------------------------------- /qlearn/toys/bootstrapped_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/facebookresearch/RandomizedValueFunctions/HEAD/qlearn/toys/bootstrapped_agent.py -------------------------------------------------------------------------------- /qlearn/toys/main_nchain.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/facebookresearch/RandomizedValueFunctions/HEAD/qlearn/toys/main_nchain.py -------------------------------------------------------------------------------- /qlearn/toys/mnf_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/facebookresearch/RandomizedValueFunctions/HEAD/qlearn/toys/mnf_agent.py -------------------------------------------------------------------------------- /qlearn/toys/model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/facebookresearch/RandomizedValueFunctions/HEAD/qlearn/toys/model.py -------------------------------------------------------------------------------- /qlearn/toys/noisy_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/facebookresearch/RandomizedValueFunctions/HEAD/qlearn/toys/noisy_agent.py -------------------------------------------------------------------------------- /qlearn/toys/test.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/facebookresearch/RandomizedValueFunctions/HEAD/qlearn/toys/test.py -------------------------------------------------------------------------------- /setup.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/facebookresearch/RandomizedValueFunctions/HEAD/setup.py --------------------------------------------------------------------------------