What is: ACER?
Source | Sample Efficient Actor-Critic with Experience Replay |
Year | 2000 |
Data Source | CC BY-SA - https://paperswithcode.com |
ACER, or Actor Critic with Experience Replay, is an actor-critic deep reinforcement learning agent with experience replay. It can be seen as an off-policy extension of A3C, where the off-policy estimator is made feasible by:
- Using Retrace Q-value estimation.
- Using truncated importance sampling with bias correction.
- Using a trust region policy optimization method.
- Using a stochastic dueling network architecture.