Learning task-relevant representations via rewards and real actions for reinforcement learning.
Linghui YuanXiaowei LuYunlong LiuPublished in: Knowl. Based Syst. (2024)
Keyphrases
- reinforcement learning
- learning process
- learned knowledge
- partially observable
- learning systems
- function approximation
- learning problems
- action selection
- model free
- learning algorithm
- autonomous learning
- state action
- goal directed
- learning mechanism
- state space
- machine learning
- multiagent reinforcement learning
- reinforcement learning algorithms
- learning capabilities
- mobile robot
- multi agent
- temporal difference learning
- intelligent behavior
- bandit problems