SCORE: Spurious COrrelation REduction for Offline Reinforcement Learning.
Zhihong DengZuyue FuLingxiao WangZhuoran YangChenjia BaiZhaoran WangJing JiangPublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- function approximation
- state space
- markov decision processes
- robotic control
- model free
- optimal policy
- correlation coefficient
- high correlation
- real time
- multi agent
- machine learning
- dynamic programming
- learning process
- learning classifier systems
- website
- action selection
- power law
- learning capabilities
- temporal difference learning
- stochastic approximation
- multi agent reinforcement learning
- real world