Generalizing Objective-Specification in Markov Decision Processes.
Pedro P. SantosPublished in: AAMAS (2024)
Keyphrases
- markov decision processes
- policy iteration
- finite state
- reinforcement learning
- optimal policy
- state space
- dynamic programming
- reinforcement learning algorithms
- transition matrices
- decision theoretic planning
- planning under uncertainty
- average cost
- partially observable
- finite horizon
- average reward
- infinite horizon
- reachability analysis
- factored mdps
- action sets
- model based reinforcement learning
- markov decision process
- search algorithm
- discounted reward
- state and action spaces
- reward function
- decision processes
- action space
- machine learning