Large Scale Markov Decision Processes with Changing Rewards.
Adrian Rivera CardosoHe WangHuan XuPublished in: NeurIPS (2019)
Keyphrases
- markov decision processes
- state space
- finite state
- reinforcement learning
- transition matrices
- reward function
- reinforcement learning algorithms
- dynamic programming
- optimal policy
- partially observable
- action space
- reachability analysis
- planning under uncertainty
- policy iteration
- finite horizon
- factored mdps
- risk sensitive
- sequential decision making under uncertainty
- infinite horizon
- markov decision process
- action sets
- model based reinforcement learning
- machine learning
- decision theoretic planning
- average reward
- discounted reward
- decision processes
- state abstraction
- markov chain
- interval estimation