Is it possible to implement a prioritized replay buffer (PER) in a TD3 agent?
4 次查看(过去 30 天)
显示 更早的评论
Hey,
I' trying to implement a TD3 Agent using MATLAB. But instead of using a replay buffer that randomly chooses samples to use in the mini batch, I would like to implememt a prioritized replay buffer instead. Until now, I couldn't find a agent option to do so.
I would be very grateful if somebody could help me with my problem.
Thanks in advance for the answers.
best regards
Michael
0 个评论
回答(1 个)
Ahmed R. Sayed
2022-9-30
By default, built-in off-policy agents (DQN, DDPG, TD3, SAC, MBPO) use an rlReplayMemory object as their experience buffer. Agents uniformly sample data from this buffer. To perform nonuniform prioritized sampling [1], which can improve sample efficiency when training your agent, use an rlPrioritizedReplayMemory object. Please refere to rlprioritizedreplaymemory.
[1] Schaul, Tom, John Quan, Ioannis Antonoglou, and David Silver. 'Prioritized experience replay'. arXiv:1511.05952 [Cs] 25 February 2016. https://arxiv.org/abs/1511.05952.
0 个评论
另请参阅
类别
在 Help Center 和 File Exchange 中查找有关 Training and Simulation 的更多信息
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!