Online Reinforcement Learning in Periodic MDP.
Ayush AniketArpan ChattopadhyayPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- markov decision processes
- optimal policy
- markov decision process
- state space
- online learning
- function approximation
- partially observable
- reward function
- action space
- reinforcement learning algorithms
- state and action spaces
- dynamic programming
- real time
- learning algorithm
- policy search
- multi agent
- machine learning
- action sets
- approximate dynamic programming
- bayesian reinforcement learning
- average reward
- policy iteration
- temporal difference
- learning process
- website
- state abstraction
- linear program