Online Reinforcement Learning in Periodic MDP.
Ayush AniketArpan ChattopadhyayPublished in: IEEE Trans. Artif. Intell. (2024)
Keyphrases
- reinforcement learning
- markov decision processes
- optimal policy
- markov decision process
- state space
- function approximation
- reinforcement learning algorithms
- learning algorithm
- real time
- partially observable
- reward function
- action sets
- supervised learning
- continuous state
- policy iteration
- inverse reinforcement learning
- balancing exploration and exploitation
- markov decision problems
- average reward
- machine learning
- temporal difference
- online communities
- decision problems
- initial state
- infinite horizon
- action space
- function approximators
- learning problems
- batch mode
- learning tasks
- online learning
- linear programming
- social media