Episodic Reinforcement Learning with Expanded State-reward Space.
Dayang LiangYaru ZhangYunlong LiuPublished in: AAMAS (2024)
Keyphrases
- reinforcement learning
- state space
- action space
- function approximation
- reward function
- learning algorithm
- multi agent
- search space
- hidden state
- machine learning
- state action
- reinforcement learning algorithms
- model free
- optimal control
- state abstraction
- low dimensional
- state and action spaces
- perceptual aliasing
- agent receives
- learning problems
- markov decision processes
- transfer learning
- optimal policy
- genetic algorithm