Online Markov Decision Processes with Non-oblivious Strategic Adversary.
Le Cong DinhDavid Henry MguniLong Tran-ThanhJun WangYaodong YangPublished in: CoRR (2021)
Keyphrases
- markov decision processes
- optimal policy
- state space
- reinforcement learning
- finite state
- planning under uncertainty
- transition matrices
- policy iteration
- finite horizon
- model based reinforcement learning
- reachability analysis
- factored mdps
- action space
- average cost
- decision theoretic planning
- infinite horizon
- dynamic programming
- markov decision process
- risk sensitive
- state abstraction
- partially observable
- decision making
- decision processes
- state and action spaces
- real time dynamic programming
- average reward
- reinforcement learning algorithms
- semi markov decision processes
- partially observable markov decision processes