Basic versions of agents from Spinning Up in Deep RL written in PyTorch. Work in progress.

To see differences between algorithms, try running diff -y <file1> <file2>, e.g., diff -y ddpg.py td3.py.

• Vanilla Policy Gradient (vpg.py)
• Trust Region Policy Gradient (trpo.py)
• Proximal Policy Optimization (ppo.py)
• Deep Deterministic Policy Gradient (ddpg.py)
• Twin Delayed DDPG (td3.py)
• Soft Actor-Critic (sac.py)

• Spinning Up in Deep RL (TensorFlow)
• Fired Up in Deep RL (PyTorch)