├── .gitignore ├── README.md ├── cmp_priority.py ├── config.py ├── data ├── priority-optioncritic-fourrooms-baseline_True-discount_0.9-epsilon_0.01-lr_critic_0.5-lr_intra_0.25-lr_term_0.25-nepisodes_5000-noptions_4-nruns_100-nsteps_1000-primitive_False-priority_1.0-temperature_0.01.npy ├── priority-optioncritic-fourrooms-baseline_True-discount_0.9-epsilon_0.01-lr_critic_0.5-lr_intra_0.25-lr_term_0.25-nepisodes_5000-noptions_4-nruns_100-nsteps_1000-primitive_False-priority_10.0-temperature_0.01.npy ├── priority-optioncritic-fourrooms-baseline_True-discount_0.9-epsilon_0.01-lr_critic_0.5-lr_intra_0.25-lr_term_0.25-nepisodes_5000-noptions_4-nruns_100-nsteps_1000-primitive_False-priority_2.0-temperature_0.01.npy ├── priority-optioncritic-fourrooms-baseline_True-discount_0.9-epsilon_0.01-lr_critic_0.5-lr_intra_0.25-lr_term_0.25-nepisodes_5000-noptions_4-nruns_100-nsteps_1000-primitive_False-priority_20.0-temperature_0.01.npy ├── priority-optioncritic-fourrooms-baseline_True-discount_0.9-epsilon_0.01-lr_critic_0.5-lr_intra_0.25-lr_term_0.25-nepisodes_5000-noptions_4-nruns_100-nsteps_1000-primitive_False-priority_5.0-temperature_0.01.npy ├── priority-optioncritic-fourrooms-baseline_True-discount_0.9-epsilon_0.01-lr_critic_0.5-lr_intra_0.25-lr_term_0.25-nepisodes_50000-noptions_4-nruns_1-nsteps_1000-primitive_False-priority_1.0-temperature_0.01.pl ├── priority-optioncritic-fourrooms-baseline_True-discount_0.9-epsilon_0.01-lr_critic_0.5-lr_intra_0.25-lr_term_0.25-nepisodes_50000-noptions_4-nruns_1-nsteps_1000-primitive_False-priority_20.0-temperature_0.01.pl └── priority-optioncritic-fourrooms-baseline_True-discount_0.9-epsilon_0.01-lr_critic_0.5-lr_intra_0.25-lr_term_0.25-nepisodes_50000-noptions_4-nruns_1-nsteps_1000-primitive_False-priority_5.0-temperature_0.01.pl ├── fourrooms.py ├── images ├── durations.png ├── formulation.png ├── pterm-eta_1-opt_4-1.png ├── pterm-eta_1-opt_4-2.png ├── pterm-eta_1-opt_4-3.png ├── pterm-eta_1-opt_4-4.png ├── pterm-eta_20-opt_4-1.png ├── pterm-eta_20-opt_4-2.png ├── pterm-eta_20-opt_4-3.png ├── pterm-eta_20-opt_4-4.png ├── pterm-eta_5-opt_4-1.png ├── pterm-eta_5-opt_4-2.png ├── pterm-eta_5-opt_4-3.png ├── pterm-eta_5-opt_4-4.png └── steps.png ├── transfer_priority.py └── view_option.py /.gitignore: -------------------------------------------------------------------------------- 1 | .idea/ 2 | __pycache__/ 3 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YuejiangLIU/prioritized_option_critic/HEAD/README.md -------------------------------------------------------------------------------- /cmp_priority.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YuejiangLIU/prioritized_option_critic/HEAD/cmp_priority.py -------------------------------------------------------------------------------- /config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YuejiangLIU/prioritized_option_critic/HEAD/config.py -------------------------------------------------------------------------------- /data/priority-optioncritic-fourrooms-baseline_True-discount_0.9-epsilon_0.01-lr_critic_0.5-lr_intra_0.25-lr_term_0.25-nepisodes_5000-noptions_4-nruns_100-nsteps_1000-primitive_False-priority_1.0-temperature_0.01.npy: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YuejiangLIU/prioritized_option_critic/HEAD/data/priority-optioncritic-fourrooms-baseline_True-discount_0.9-epsilon_0.01-lr_critic_0.5-lr_intra_0.25-lr_term_0.25-nepisodes_5000-noptions_4-nruns_100-nsteps_1000-primitive_False-priority_1.0-temperature_0.01.npy -------------------------------------------------------------------------------- /data/priority-optioncritic-fourrooms-baseline_True-discount_0.9-epsilon_0.01-lr_critic_0.5-lr_intra_0.25-lr_term_0.25-nepisodes_5000-noptions_4-nruns_100-nsteps_1000-primitive_False-priority_10.0-temperature_0.01.npy: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YuejiangLIU/prioritized_option_critic/HEAD/data/priority-optioncritic-fourrooms-baseline_True-discount_0.9-epsilon_0.01-lr_critic_0.5-lr_intra_0.25-lr_term_0.25-nepisodes_5000-noptions_4-nruns_100-nsteps_1000-primitive_False-priority_10.0-temperature_0.01.npy -------------------------------------------------------------------------------- /data/priority-optioncritic-fourrooms-baseline_True-discount_0.9-epsilon_0.01-lr_critic_0.5-lr_intra_0.25-lr_term_0.25-nepisodes_5000-noptions_4-nruns_100-nsteps_1000-primitive_False-priority_2.0-temperature_0.01.npy: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YuejiangLIU/prioritized_option_critic/HEAD/data/priority-optioncritic-fourrooms-baseline_True-discount_0.9-epsilon_0.01-lr_critic_0.5-lr_intra_0.25-lr_term_0.25-nepisodes_5000-noptions_4-nruns_100-nsteps_1000-primitive_False-priority_2.0-temperature_0.01.npy -------------------------------------------------------------------------------- /data/priority-optioncritic-fourrooms-baseline_True-discount_0.9-epsilon_0.01-lr_critic_0.5-lr_intra_0.25-lr_term_0.25-nepisodes_5000-noptions_4-nruns_100-nsteps_1000-primitive_False-priority_20.0-temperature_0.01.npy: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YuejiangLIU/prioritized_option_critic/HEAD/data/priority-optioncritic-fourrooms-baseline_True-discount_0.9-epsilon_0.01-lr_critic_0.5-lr_intra_0.25-lr_term_0.25-nepisodes_5000-noptions_4-nruns_100-nsteps_1000-primitive_False-priority_20.0-temperature_0.01.npy -------------------------------------------------------------------------------- /data/priority-optioncritic-fourrooms-baseline_True-discount_0.9-epsilon_0.01-lr_critic_0.5-lr_intra_0.25-lr_term_0.25-nepisodes_5000-noptions_4-nruns_100-nsteps_1000-primitive_False-priority_5.0-temperature_0.01.npy: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YuejiangLIU/prioritized_option_critic/HEAD/data/priority-optioncritic-fourrooms-baseline_True-discount_0.9-epsilon_0.01-lr_critic_0.5-lr_intra_0.25-lr_term_0.25-nepisodes_5000-noptions_4-nruns_100-nsteps_1000-primitive_False-priority_5.0-temperature_0.01.npy -------------------------------------------------------------------------------- /data/priority-optioncritic-fourrooms-baseline_True-discount_0.9-epsilon_0.01-lr_critic_0.5-lr_intra_0.25-lr_term_0.25-nepisodes_50000-noptions_4-nruns_1-nsteps_1000-primitive_False-priority_1.0-temperature_0.01.pl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YuejiangLIU/prioritized_option_critic/HEAD/data/priority-optioncritic-fourrooms-baseline_True-discount_0.9-epsilon_0.01-lr_critic_0.5-lr_intra_0.25-lr_term_0.25-nepisodes_50000-noptions_4-nruns_1-nsteps_1000-primitive_False-priority_1.0-temperature_0.01.pl -------------------------------------------------------------------------------- /data/priority-optioncritic-fourrooms-baseline_True-discount_0.9-epsilon_0.01-lr_critic_0.5-lr_intra_0.25-lr_term_0.25-nepisodes_50000-noptions_4-nruns_1-nsteps_1000-primitive_False-priority_20.0-temperature_0.01.pl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YuejiangLIU/prioritized_option_critic/HEAD/data/priority-optioncritic-fourrooms-baseline_True-discount_0.9-epsilon_0.01-lr_critic_0.5-lr_intra_0.25-lr_term_0.25-nepisodes_50000-noptions_4-nruns_1-nsteps_1000-primitive_False-priority_20.0-temperature_0.01.pl -------------------------------------------------------------------------------- /data/priority-optioncritic-fourrooms-baseline_True-discount_0.9-epsilon_0.01-lr_critic_0.5-lr_intra_0.25-lr_term_0.25-nepisodes_50000-noptions_4-nruns_1-nsteps_1000-primitive_False-priority_5.0-temperature_0.01.pl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YuejiangLIU/prioritized_option_critic/HEAD/data/priority-optioncritic-fourrooms-baseline_True-discount_0.9-epsilon_0.01-lr_critic_0.5-lr_intra_0.25-lr_term_0.25-nepisodes_50000-noptions_4-nruns_1-nsteps_1000-primitive_False-priority_5.0-temperature_0.01.pl -------------------------------------------------------------------------------- /fourrooms.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YuejiangLIU/prioritized_option_critic/HEAD/fourrooms.py -------------------------------------------------------------------------------- /images/durations.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YuejiangLIU/prioritized_option_critic/HEAD/images/durations.png -------------------------------------------------------------------------------- /images/formulation.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YuejiangLIU/prioritized_option_critic/HEAD/images/formulation.png -------------------------------------------------------------------------------- /images/pterm-eta_1-opt_4-1.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YuejiangLIU/prioritized_option_critic/HEAD/images/pterm-eta_1-opt_4-1.png -------------------------------------------------------------------------------- /images/pterm-eta_1-opt_4-2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YuejiangLIU/prioritized_option_critic/HEAD/images/pterm-eta_1-opt_4-2.png -------------------------------------------------------------------------------- /images/pterm-eta_1-opt_4-3.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YuejiangLIU/prioritized_option_critic/HEAD/images/pterm-eta_1-opt_4-3.png -------------------------------------------------------------------------------- /images/pterm-eta_1-opt_4-4.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YuejiangLIU/prioritized_option_critic/HEAD/images/pterm-eta_1-opt_4-4.png -------------------------------------------------------------------------------- /images/pterm-eta_20-opt_4-1.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YuejiangLIU/prioritized_option_critic/HEAD/images/pterm-eta_20-opt_4-1.png -------------------------------------------------------------------------------- /images/pterm-eta_20-opt_4-2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YuejiangLIU/prioritized_option_critic/HEAD/images/pterm-eta_20-opt_4-2.png -------------------------------------------------------------------------------- /images/pterm-eta_20-opt_4-3.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YuejiangLIU/prioritized_option_critic/HEAD/images/pterm-eta_20-opt_4-3.png -------------------------------------------------------------------------------- /images/pterm-eta_20-opt_4-4.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YuejiangLIU/prioritized_option_critic/HEAD/images/pterm-eta_20-opt_4-4.png -------------------------------------------------------------------------------- /images/pterm-eta_5-opt_4-1.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YuejiangLIU/prioritized_option_critic/HEAD/images/pterm-eta_5-opt_4-1.png -------------------------------------------------------------------------------- /images/pterm-eta_5-opt_4-2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YuejiangLIU/prioritized_option_critic/HEAD/images/pterm-eta_5-opt_4-2.png -------------------------------------------------------------------------------- /images/pterm-eta_5-opt_4-3.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YuejiangLIU/prioritized_option_critic/HEAD/images/pterm-eta_5-opt_4-3.png -------------------------------------------------------------------------------- /images/pterm-eta_5-opt_4-4.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YuejiangLIU/prioritized_option_critic/HEAD/images/pterm-eta_5-opt_4-4.png -------------------------------------------------------------------------------- /images/steps.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YuejiangLIU/prioritized_option_critic/HEAD/images/steps.png -------------------------------------------------------------------------------- /transfer_priority.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YuejiangLIU/prioritized_option_critic/HEAD/transfer_priority.py -------------------------------------------------------------------------------- /view_option.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YuejiangLIU/prioritized_option_critic/HEAD/view_option.py --------------------------------------------------------------------------------