On learning history-based policies for controlling Markov decision processes.
Gandharv PatilAditya MahajanDoina PrecupPublished in: AISTATS (2024)
Keyphrases
- markov decision processes
- reinforcement learning
- optimal policy
- partially observable
- macro actions
- markov decision process
- supervised learning
- state space
- model based reinforcement learning
- learning algorithm
- policy iteration
- decision theoretic planning
- decision processes
- infinite horizon
- stochastic games
- finite state
- decision problems
- action sets
- reachability analysis
- dynamic programming
- transition matrices