Unsupervised Domain Adaptation with Dynamics-Aware Rewards in Reinforcement Learning.
Jinxin LiuHao ShenDonglin WangYachen KangQiangxing TianPublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- markov decision processes
- function approximation
- state space
- learning algorithm
- reinforcement learning algorithms
- temporal difference
- robotic control
- supervised learning
- optimal policy
- dynamic model
- model free
- learning capabilities
- reward shaping
- hidden markov models
- learning process
- multi agent
- reward function
- multi agent reinforcement learning
- data sets
- complex domains
- policy iteration