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 (RL) | 253 | 32.15% |
Continual Learning | 57 | 7.24% |
Continuous Control | 47 | 5.97% |
Decision Making | 32 | 4.07% |
Multi-agent Reinforcement Learning | 23 | 2.92% |
OpenAI Gym | 23 | 2.92% |
Atari Games | 17 | 2.16% |
Management | 16 | 2.03% |
Incremental Learning | 15 | 1.91% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |