Online Learning with Implicit Exploration in Episodic Markov Decision Processes.
Mahsa GhasemiAbolfazl HashemiHaris VikaloUfuk TopcuPublished in: ACC (2021)
Keyphrases
- markov decision processes
- online learning
- model based reinforcement learning
- interval estimation
- optimal policy
- reinforcement learning
- state space
- finite state
- dynamic programming
- decision theoretic planning
- reinforcement learning algorithms
- decision processes
- transition matrices
- finite horizon
- partially observable
- reachability analysis
- e learning
- policy iteration
- risk sensitive
- infinite horizon
- active learning
- factored mdps
- average reward
- action sets
- semi markov decision processes
- markov decision process
- probabilistic planning
- average cost
- state and action spaces
- action space
- search space
- monte carlo
- real time dynamic programming