Error-Aware Policy Learning: Zero-Shot Generalization in Partially Observable Dynamic Environments.
Visak C. V. KumarSehoon HaC. Karen LiuPublished in: CoRR (2021)
Keyphrases
- dynamic environments
- partially observable
- partially observable environments
- reinforcement learning
- state space
- belief space
- learning algorithm
- decision problems
- partially observable domains
- markov decision problems
- action models
- autonomous agents
- partial observability
- inverse reinforcement learning
- infinite horizon
- optimal policy
- reinforcement learning agents
- special case
- autonomous robots
- belief state
- path planning
- mobile robot