02/02/2021

Reinforcement Learning with Trajectory Feedback

Yonathan Efroni, Nadav Merlis, Shie Mannor

Keywords:

Abstract Paper Similar Papers

Abstract: The standard feedback model of reinforcement learning requires revealing the reward of every visited state-action pair. However, in practice, it is often the case that such frequent feedback is not available. In this work, we take a first step towards relaxing this assumption and require a weaker form of feedback, which we refer to as \emph{trajectory feedback}. Instead of observing the reward obtained after every action, we assume we only receive a score that represents the quality of the whole trajectory observed by the agent, namely, the sum of all rewards obtained over this trajectory. We extend reinforcement learning algorithms to this setting, based on least-squares estimation of the unknown reward, for both the known and unknown transition model cases, and study the performance of these algorithms by analyzing their regret. For cases where the transition model is unknown, we offer a hybrid optimistic-Thompson Sampling approach that results in a tractable algorithm.

The video of this talk cannot be embedded. You can watch it here:
https://slideslive.com/38948557
(Link will open in new window)
 0
 0
 0
 0
  Share    
This is an embedded video. Talk and the respective paper are published at AAAI 2021 virtual conference. If you are one of the authors of the paper and want to manage your upload, see the question "My papertalk has been externally embedded..." in the FAQ section.

Comments

Post Comment
no comments yet
code of conduct: tbd Characters remaining: 140

Similar Papers

 0
 0
 0
 0
 18:07 
 0
 0
 0
 0
 14:14 
 0
 0
 0
 0
 11:47 
 0
 0
 0
 0
 13:26 
 0
 0
 0
 0
 14:52 
 0
 0
 0
 0
 14:22 
 0
 0
 0
 0
 18:34 
 0
 0
 0
 0
 13:11 
 0
 0
 0
 0
 10:52 
 0
 0
 0
 0
 16:14 
 0
 0
 0
 0
 7:57 
 0
 0
 0
 0
 13:27 
 0
 0
 0
 0
 2:41 
 0
 0
 0
 0
 18:27 
 0
 0
 0
 0
 15:20 
 0
 0
 0
 0
 3:12 
 0
 0
 0
 0
 13:24 
 0
 0
 0
 0
 3:20 
 0
 0
 0
 0
 5:43 
 0
 0
 0
 0
 12:07 
 0
 0
 0
 0
 5:14 
 0
 0
 0
 0
 5:20 
 0
 0
 0
 0
 3:24 
 0
 0
 0
 0
 12:25 
 0
 0
 0
 0
 5:58 
 0
 0
 0
 0
 3:18 
 0
 0
 0
 0
 4:38 
 0
 0
 0
 0
 3:11 
 0
 0
 0
 0
 3:07 
 0
 0
 0
 0
 5:20 
 0
 0
 0
 0
 14:13 
 0
 0
 0
 0
 20:29 
 0
 0
 0
 0
 15:06 
 0
 0
 0
 0
 14:22 
 0
 0
 0
 0
 15:07 
 0
 0
 0
 0
 3:14 
 0
 0
 0
 0
 14:36 
 0
 0
 0
 0
 20:41 
 0
 0
 0
 0
 7:49 
 0
 0
 0
 0
 11:33