| Definition | This is a collection of curiosity algorithms implemented in pytorch on top of the rlpyt deep rl codebase. |
| No of environments | 135 |
Available Learning Algorithms
Policy Gradient A2C, PPO
Replay Buffers (supporting both DQN + QPG) non-sequence and sequence (for recurrent) replay, n-step returns, uniform or prioritized replay, full-observation or frame-based buffer (e.g. for Atari, stores only unique frames to save memory, reconstructs multi-frame observations).
Deep Q-Learning DQN + variants: Double, Dueling, Categorical (up to Rainbow minus Noisy Nets), Recurrent (R2D2-style)
Q-Function Policy Gradient DDPG, TD3, SAC
Available Curiosity Algorithms
Prediction error ICM, Disagreement
Count-based RND
Learning progress NDIGO
Available Environments
Standard gym environments (mujoco, etc.)
Atari environments
SuperMarioBros
Deepmind PyColab