Episodic Reinforcement Learning with Expanded State-reward Space.
Dayang LiangYaru ZhangYunlong LiuPublished in: CoRR (2024)
Keyphrases
- reinforcement learning
- state space
- action space
- search space
- total reward
- markov decision processes
- multi agent
- learning algorithm
- temporal difference
- learning process
- function approximation
- eligibility traces
- state action
- state abstraction
- agent receives
- transition model
- reinforcement learning algorithms
- state variables
- optimal policy
- low dimensional