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