Login / Signup

Zero-shot Policy Learning with Spatial Temporal Reward Decomposition on Contingency-aware Observation.

Huazhe XuBoyuan ChenYang GaoTrevor Darrell
Published in: ICRA (2021)
Keyphrases
  • spatial temporal
  • reinforcement learning
  • inverse reinforcement learning
  • spatio temporal
  • partially observable environments
  • object recognition
  • policy gradient
  • high level
  • temporal information