Near-optimal Conservative Exploration in Reinforcement Learning under Episode-wise Constraints.
Donghao LiRuiquan HuangCong ShenJing YangPublished in: ICML (2023)
Keyphrases
- reinforcement learning
- active exploration
- function approximation
- state space
- resource constraints
- exploration strategy
- exploration exploitation
- multi agent
- constraint satisfaction
- constraint programming
- action selection
- neural network
- geometric constraints
- constrained optimization
- model free
- temporal difference
- linear constraints