Experience Replay is a replay memory technique used in reinforcement learning where we store the agent’s experiences at each time-step, $e_{t} = \left(s_{t}, a_{t}, r_{t}, s_{t+1}\right)$ in a data-set $D = e_{1}, \cdots, e_{N}$ , pooled over many episodes into a replay memory. We then usually sample the memory randomly for a minibatch of experience, and use this to learn off-policy, as with Deep Q-Networks. This tackles the problem of autocorrelation leading to unstable training, by making the problem more like a supervised learning problem.
Image Credit: Hands-On Reinforcement Learning with Python, Sudharsan Ravichandiran
Paper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
reinforcement-learning | 296 | 39.05% |
Continuous Control | 68 | 8.97% |
Continual Learning | 43 | 5.67% |
OpenAI Gym | 34 | 4.49% |
Atari Games | 27 | 3.56% |
Multi-agent Reinforcement Learning | 22 | 2.90% |
Decision Making | 21 | 2.77% |
Imitation Learning | 17 | 2.24% |
DeepMind | 13 | 1.72% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |