Post-Episodic Reinforcement Learning Inference.
Vasilis SyrgkanisRuohan ZhanPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- reinforcement learning algorithms
- state space
- inference process
- function approximation
- inference mechanism
- temporal difference
- genetic algorithm
- multi agent
- learning process
- markov decision processes
- learning problems
- model free
- optimal policy
- robot control
- bayesian model
- data sets
- bayesian networks
- case study
- decision making
- data mining