Reinforcement learning with Demonstrations from Mismatched Task under Sparse Reward.
Yanjiang GuoJingyue GaoZheng WuChengming ShiJianyu ChenPublished in: CoRL (2022)
Keyphrases
- reinforcement learning
- function approximation
- state space
- multi agent
- model free
- learning algorithm
- sparse data
- reinforcement learning algorithms
- optimal control
- high dimensional
- temporal difference
- supervised learning
- optimal policy
- sparse representation
- eligibility traces
- markov decision processes
- average reward
- total reward
- learning process
- learning capabilities
- partially observable environments
- action selection
- sparse coding
- feature selection
- reward function
- compressive sensing
- temporal difference learning
- transfer learning
- dynamic programming
- robotic control