Strategies for MDP Bisimilarity Equivalence and Inequivalence.
Stefan KieferQiyi TangPublished in: CONCUR (2022)
Keyphrases
- markov decision processes
- markov decision process
- linear programming
- utility function
- finite state
- real time
- artificial intelligence
- decision theoretic
- optimal policy
- search strategies
- exploration strategy
- optimal strategy
- online auctions
- linear program
- reinforcement learning
- decision making
- genetic algorithm
- data sets