Error-Aware Policy Learning: Zero-Shot Generalization in Partially Observable Dynamic Environments.
Visak C. V. KumarSehoon HaC. Karen LiuPublished in: Robotics: Science and Systems (2021)
Keyphrases
- partially observable
- dynamic environments
- partially observable environments
- reinforcement learning
- dynamical systems
- belief space
- action models
- decision problems
- markov decision problems
- partial observations
- learning algorithm
- markov decision processes
- state space
- changing environment
- path planning
- partial observability
- reinforcement learning agents
- single agent
- optimal policy
- mobile robot
- partially observable domains
- reinforcement learning algorithms
- inverse reinforcement learning
- hidden state
- learning agent
- autonomous agents
- decision making