├── .gitignore ├── Dockerfile ├── README.md ├── docker-compose.yaml ├── environment.yml ├── examples ├── mujoco_all_sql.py ├── mujoco_all_sql_remote.py ├── multigoal_sql.py ├── pusher_combine.py ├── pusher_pretrain.py └── reuse_qf_policy_swimmer.py ├── models └── pusher.xml ├── scripts └── sim_policy.py └── softqlearning ├── __init__.py ├── algorithms ├── __init__.py ├── rl_algorithm.py └── sql.py ├── environments ├── __init__.py ├── delayed_env.py ├── gym_env.py ├── multigoal.py └── pusher.py ├── misc ├── __init__.py ├── instrument.py ├── kernel.py ├── nn.py ├── plotter.py ├── remote_sampler.py ├── sampler.py ├── tf_utils.py └── utils.py ├── policies ├── __init__.py ├── nn_policy.py └── stochastic_policy.py ├── replay_buffers ├── __init__.py ├── replay_buffer.py ├── simple_replay_buffer.py └── union_buffer.py └── value_functions ├── __init__.py └── value_function.py /.gitignore: -------------------------------------------------------------------------------- 1 | data 2 | *.pyc 3 | .idea 4 | MUJOCO_LOG.TXT 5 | venv/ 6 | -------------------------------------------------------------------------------- /Dockerfile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haarnoja/softqlearning/HEAD/Dockerfile -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haarnoja/softqlearning/HEAD/README.md -------------------------------------------------------------------------------- /docker-compose.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haarnoja/softqlearning/HEAD/docker-compose.yaml -------------------------------------------------------------------------------- /environment.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haarnoja/softqlearning/HEAD/environment.yml -------------------------------------------------------------------------------- /examples/mujoco_all_sql.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haarnoja/softqlearning/HEAD/examples/mujoco_all_sql.py -------------------------------------------------------------------------------- /examples/mujoco_all_sql_remote.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haarnoja/softqlearning/HEAD/examples/mujoco_all_sql_remote.py -------------------------------------------------------------------------------- /examples/multigoal_sql.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haarnoja/softqlearning/HEAD/examples/multigoal_sql.py -------------------------------------------------------------------------------- /examples/pusher_combine.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haarnoja/softqlearning/HEAD/examples/pusher_combine.py -------------------------------------------------------------------------------- /examples/pusher_pretrain.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haarnoja/softqlearning/HEAD/examples/pusher_pretrain.py -------------------------------------------------------------------------------- /examples/reuse_qf_policy_swimmer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haarnoja/softqlearning/HEAD/examples/reuse_qf_policy_swimmer.py -------------------------------------------------------------------------------- /models/pusher.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haarnoja/softqlearning/HEAD/models/pusher.xml -------------------------------------------------------------------------------- /scripts/sim_policy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haarnoja/softqlearning/HEAD/scripts/sim_policy.py -------------------------------------------------------------------------------- /softqlearning/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /softqlearning/algorithms/__init__.py: -------------------------------------------------------------------------------- 1 | from .sql import SQL 2 | -------------------------------------------------------------------------------- /softqlearning/algorithms/rl_algorithm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haarnoja/softqlearning/HEAD/softqlearning/algorithms/rl_algorithm.py -------------------------------------------------------------------------------- /softqlearning/algorithms/sql.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haarnoja/softqlearning/HEAD/softqlearning/algorithms/sql.py -------------------------------------------------------------------------------- /softqlearning/environments/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haarnoja/softqlearning/HEAD/softqlearning/environments/__init__.py -------------------------------------------------------------------------------- /softqlearning/environments/delayed_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haarnoja/softqlearning/HEAD/softqlearning/environments/delayed_env.py -------------------------------------------------------------------------------- /softqlearning/environments/gym_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haarnoja/softqlearning/HEAD/softqlearning/environments/gym_env.py -------------------------------------------------------------------------------- /softqlearning/environments/multigoal.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haarnoja/softqlearning/HEAD/softqlearning/environments/multigoal.py -------------------------------------------------------------------------------- /softqlearning/environments/pusher.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haarnoja/softqlearning/HEAD/softqlearning/environments/pusher.py -------------------------------------------------------------------------------- /softqlearning/misc/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /softqlearning/misc/instrument.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haarnoja/softqlearning/HEAD/softqlearning/misc/instrument.py -------------------------------------------------------------------------------- /softqlearning/misc/kernel.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haarnoja/softqlearning/HEAD/softqlearning/misc/kernel.py -------------------------------------------------------------------------------- /softqlearning/misc/nn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haarnoja/softqlearning/HEAD/softqlearning/misc/nn.py -------------------------------------------------------------------------------- /softqlearning/misc/plotter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haarnoja/softqlearning/HEAD/softqlearning/misc/plotter.py -------------------------------------------------------------------------------- /softqlearning/misc/remote_sampler.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haarnoja/softqlearning/HEAD/softqlearning/misc/remote_sampler.py -------------------------------------------------------------------------------- /softqlearning/misc/sampler.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haarnoja/softqlearning/HEAD/softqlearning/misc/sampler.py -------------------------------------------------------------------------------- /softqlearning/misc/tf_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haarnoja/softqlearning/HEAD/softqlearning/misc/tf_utils.py -------------------------------------------------------------------------------- /softqlearning/misc/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haarnoja/softqlearning/HEAD/softqlearning/misc/utils.py -------------------------------------------------------------------------------- /softqlearning/policies/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haarnoja/softqlearning/HEAD/softqlearning/policies/__init__.py -------------------------------------------------------------------------------- /softqlearning/policies/nn_policy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haarnoja/softqlearning/HEAD/softqlearning/policies/nn_policy.py -------------------------------------------------------------------------------- /softqlearning/policies/stochastic_policy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haarnoja/softqlearning/HEAD/softqlearning/policies/stochastic_policy.py -------------------------------------------------------------------------------- /softqlearning/replay_buffers/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haarnoja/softqlearning/HEAD/softqlearning/replay_buffers/__init__.py -------------------------------------------------------------------------------- /softqlearning/replay_buffers/replay_buffer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haarnoja/softqlearning/HEAD/softqlearning/replay_buffers/replay_buffer.py -------------------------------------------------------------------------------- /softqlearning/replay_buffers/simple_replay_buffer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haarnoja/softqlearning/HEAD/softqlearning/replay_buffers/simple_replay_buffer.py -------------------------------------------------------------------------------- /softqlearning/replay_buffers/union_buffer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haarnoja/softqlearning/HEAD/softqlearning/replay_buffers/union_buffer.py -------------------------------------------------------------------------------- /softqlearning/value_functions/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haarnoja/softqlearning/HEAD/softqlearning/value_functions/__init__.py -------------------------------------------------------------------------------- /softqlearning/value_functions/value_function.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haarnoja/softqlearning/HEAD/softqlearning/value_functions/value_function.py --------------------------------------------------------------------------------