Symmetric Q-learning: Reducing Skewness of Bellman Error in Online Reinforcement Learning.
Motoki OmuraTakayuki OsaYusuke MukutaTatsuya HaradaPublished in: AAAI (2024)
Keyphrases
- function approximators
- reinforcement learning
- function approximation
- state action
- temporal difference learning
- reinforcement learning algorithms
- temporal difference
- continuous state and action spaces
- reinforcement learning problems
- online learning
- state action space
- temporal difference methods
- model free
- action selection
- learning algorithm
- state space
- error rate
- eligibility traces
- learning agent
- actor critic
- learning problems
- reinforcement learning methods
- supervised learning
- dynamic programming
- machine learning
- multi agent reinforcement learning
- optimal policy
- transfer learning
- reward function
- markov decision processes
- multi agent