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) | 189 | 17.48% |
Deep Reinforcement Learning | 160 | 14.80% |
Reinforcement Learning | 137 | 12.67% |
Continual Learning | 67 | 6.20% |
Continuous Control | 46 | 4.26% |
Decision Making | 32 | 2.96% |
Multi-agent Reinforcement Learning | 26 | 2.41% |
Incremental Learning | 18 | 1.67% |
Management | 17 | 1.57% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |