Physics Informed Intrinsic Rewards in Reinforcement Learning.
Jiazhou JiangMinyue FuZhiyong ChenPublished in: ANZCC (2022)
Keyphrases
- reinforcement learning
- markov decision processes
- function approximation
- reinforcement learning algorithms
- reward shaping
- learning algorithm
- model free
- computer science
- state space
- multi agent
- temporal difference
- reward function
- machine learning
- geometric structure
- total reward
- optimal policy
- learning process
- artificial intelligence
- learning problems
- dynamic programming
- learning capabilities
- action space
- reinforcement learning methods
- learning classifier systems
- supervised learning
- autonomous learning
- bandit problems
- multiarmed bandit