Corpus ID: 231984613

Beyond Prioritized Replay: Sampling States in Model-Based Reinforcement Learning via Simulated Priorities

@inproceedings{Mei2020BeyondPR,
  title={Beyond Prioritized Replay: Sampling States in Model-Based Reinforcement Learning via Simulated Priorities},
  author={Jincheng Mei and Yangchen Pan and Amir-massoud Farahmand and Hengshuai Yao and M. White},
  year={2020}
}
The prioritized Experience Replay (ER) method has attracted great attention; however, there is little theoretical understanding about why it can help and its limitations. In this work, we take a deep look at the prioritized ER. In a supervised learning setting, we show the equivalence between the error-based prioritized sampling method for mean squared error and uniform sampling for cubic power loss. We then provide theoretical insight into why it improves convergence rate upon uniform sampling… Expand