Cache-Efficient Memory Representation of Markov Decision Processes.
Jaël Champagne GareauÉric BeaudryVladimir MakarenkovPublished in: AI (2022)
Keyphrases
- markov decision processes
- decision theoretic planning
- finite state
- optimal policy
- transition matrices
- reachability analysis
- dynamic programming
- main memory
- reinforcement learning
- cache conscious
- reinforcement learning algorithms
- state space
- limited memory
- policy iteration
- planning under uncertainty
- decision diagrams
- markov decision process
- finite horizon
- decision processes
- risk sensitive
- average reward
- state and action spaces
- factored mdps
- machine learning
- query processing
- multistage
- markov decision problems
- average cost
- partially observable