Q-Learning Networks
Rainbow DQN
Introduced by Hessel et al. in Rainbow: Combining Improvements in Deep Reinforcement LearningRainbow DQN is an extended DQN that combines several improvements into a single learner. Specifically:
- It uses Double Q-Learning to tackle overestimation bias.
- It uses Prioritized Experience Replay to prioritize important transitions.
- It uses dueling networks.
- It uses multi-step learning.
- It uses distributional reinforcement learning instead of the expected return.
- It uses noisy linear layers for exploration.
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Reinforcement Learning (RL) | 6 | 46.15% |
| Atari Games | 2 | 15.38% |
| Decision Making | 1 | 7.69% |
| Efficient Exploration | 1 | 7.69% |
| Ensemble Learning | 1 | 7.69% |
| Game of Go | 1 | 7.69% |
| Montezuma's Revenge | 1 | 7.69% |
Double Q-learning
Dueling Network
Noisy Linear Layer
N-step Returns
Prioritized Experience Replay
