Skip to content

Modularized Implementation of Deep RL Algorithms in PyTorch

License

Notifications You must be signed in to change notification settings

ShangtongZhang/DeepRL

 
 

Repository files navigation

This branch is the code for the paper

DAC: The Double Actor-Critic Architecture for Learning Options
Shangtong Zhang, Shimon Whiteson (NeurIPS 2019)

.
├── Dockerfile                                      # Dependencies
├── requirements.txt                                # Dependencies
├── template_jobs.py                                
|   ├── batch_mujoco                                # Start Mujoco experiments 
|   ├── batch_dm                                    # Start DMControl experiments 
|   ├── a_squared_c_ppo_continuous                  # Entrance of DAC+PPO
├── deep_rl/agent/ASquaredC_PPO_agent.py            # Implementation of DAC+PPO 
├── deep_rl/agent/ASquaredC_A2C_agent.py            # Implementation of DAC+A2C 
├── deep_rl/agent/AHP_PPO_agent.py                  # Implementation of AHP+PPO 
├── deep_rl/agent/IOPG_agent.py                     # Implementation of IOPG 
├── deep_rl/agent/OC_agent.py                       # Implementation of OC 
├── deep_rl/agent/PPOC_agent.py                     # Implementation of PPOC 
├── deep_rl/component/cheetah_backward.py           # Cheetah-Backward 
├── deep_rl/component/walker_ex.py                  # Walker-Backward/Squat 
├── deep_rl/component/fish_downleft.py              # Fish-Downleft 
└── plot_paper.py                                   # Plotting

I can send the data for plotting via email upon request.

This branch is based on the DeepRL codebase and is left unchanged after I completed the paper. Algorithm implementations not used in the paper may be broken and should never be used. It may take extra effort if you want to rebase/merge the master branch.