├── .gitignore ├── CONTRIBUTING.md ├── LICENSE ├── README.md ├── data_example └── cartpole_0.3_example.npz ├── install.sh ├── neural ├── agent_distributed.py ├── cost.py ├── cost_environment_loop.py ├── data_util.py ├── learning.py ├── net_templates.py ├── networks.py ├── run_experiment.py └── rwrl.py ├── requirements.txt ├── run.sh └── tabular ├── mdp_util.py ├── offline_cmdp.py └── run_random_cmdp_experiment.py /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-deepmind/constrained_optidice/HEAD/.gitignore -------------------------------------------------------------------------------- /CONTRIBUTING.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-deepmind/constrained_optidice/HEAD/CONTRIBUTING.md -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-deepmind/constrained_optidice/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-deepmind/constrained_optidice/HEAD/README.md -------------------------------------------------------------------------------- /data_example/cartpole_0.3_example.npz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-deepmind/constrained_optidice/HEAD/data_example/cartpole_0.3_example.npz -------------------------------------------------------------------------------- /install.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-deepmind/constrained_optidice/HEAD/install.sh -------------------------------------------------------------------------------- /neural/agent_distributed.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-deepmind/constrained_optidice/HEAD/neural/agent_distributed.py -------------------------------------------------------------------------------- /neural/cost.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-deepmind/constrained_optidice/HEAD/neural/cost.py -------------------------------------------------------------------------------- /neural/cost_environment_loop.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-deepmind/constrained_optidice/HEAD/neural/cost_environment_loop.py -------------------------------------------------------------------------------- /neural/data_util.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-deepmind/constrained_optidice/HEAD/neural/data_util.py -------------------------------------------------------------------------------- /neural/learning.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-deepmind/constrained_optidice/HEAD/neural/learning.py -------------------------------------------------------------------------------- /neural/net_templates.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-deepmind/constrained_optidice/HEAD/neural/net_templates.py -------------------------------------------------------------------------------- /neural/networks.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-deepmind/constrained_optidice/HEAD/neural/networks.py -------------------------------------------------------------------------------- /neural/run_experiment.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-deepmind/constrained_optidice/HEAD/neural/run_experiment.py -------------------------------------------------------------------------------- /neural/rwrl.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-deepmind/constrained_optidice/HEAD/neural/rwrl.py -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-deepmind/constrained_optidice/HEAD/requirements.txt -------------------------------------------------------------------------------- /run.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-deepmind/constrained_optidice/HEAD/run.sh -------------------------------------------------------------------------------- /tabular/mdp_util.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-deepmind/constrained_optidice/HEAD/tabular/mdp_util.py -------------------------------------------------------------------------------- /tabular/offline_cmdp.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-deepmind/constrained_optidice/HEAD/tabular/offline_cmdp.py -------------------------------------------------------------------------------- /tabular/run_random_cmdp_experiment.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/google-deepmind/constrained_optidice/HEAD/tabular/run_random_cmdp_experiment.py --------------------------------------------------------------------------------