02/02/2021

Domain Adaptation In Reinforcement Learning Via Latent Unified State Representation

Jinwei Xing, Takashi Nagata, Kexin Chen, Xinyun Zou, Emre Neftci, Jeffrey L. Krichmar

Keywords:

Abstract Paper Similar Papers

Abstract: Despite the recent success of deep reinforcement learning (RL), domain adaptation remains an open problem. Although the generalization ability of RL agents is critical for the real-world applicability of Deep RL, zero-shot policy transfer is still a challenging problem since even minor visual changes could make the trained agent completely fail in the new task. To address this issue, we propose a two-stage RL agent that first learns a latent unified state representation (LUSR) which is consistent across multiple domains in the first stage, and then do RL training in one source domain based on LUSR in the second stage. The cross-domain consistency of LUSR allows the policy acquired from the source domain to generalize to other target domains without extra training. We first demonstrate our approach in variants of CarRacing games with customized manipulations, and then verify it in CARLA, an autonomous driving simulator with more complex and realistic visual observations. Our results show that this approach can achieve state-of-the-art domain adaptation performance in related RL tasks and outperforms prior approaches based on latent-representation based RL and image-to-image translation.

The video of this talk cannot be embedded. You can watch it here:
https://slideslive.com/38948688
(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

 1
 0
 0
 0
 6:21 
 0
 0
 0
 0
 14:57 
 0
 0
 0
 0
 3:29 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 4:38 
 0
 0
 0
 0
 7:25 
 0
 0
 0
 0
 12:35 
 0
 0
 0
 0
 6:48 
 0
 0
 0
 0
 4:55 
 0
 0
 0
 0
 14:04 
 0
 0
 0
 0
 15:38 
 0
 0
 0
 0
 14:12 
 0
 0
 0
 0
 8:43 
 0
 0
 0
 0
 4:01 
 0
 0
 0
 0
 3:24 
 0
 0
 0
 0
 8:34 
 0
 0
 0
 0
 14:28 
 0
 0
 0
 0
 5:27 
 0
 0
 0
 0
 12:19 
 0
 0
 0
 0
 3:30 
 0
 0
 0
 0
 10:55 
 0
 0
 0
 0
 15:19 
 0
 0
 0
 0
 5:33 
 0
 0
 0
 0
 15:13 
 0
 0
 0
 0
 3:24 
 0
 0
 0
 0
 4:52 
 0
 0
 0
 0
 8:52 
 0
 0
 0
 0
 5:15 
 0
 0
 0
 1
 5:10 
 0
 0
 0
 0
 5:04 
 0
 0
 0
 0
 13:36 
 0
 0
 0
 0
 14:48 
 0
 0
 0
 0
 12:22 
 0
 0
 0
 1
 14:20 
 0
 0
 0
 0
 3:11 
 0
 0
 0
 0
 1:00 
 0
 0
 0
 0
 5:05 
 0
 0
 0
 0
 17:15 
 0
 0
 0
 0
 3:06 
 0
 0
 0
 0
 10:40