Markov Decision Processes with Time-Varying Geometric Discounting.
Jiarui GanAnnika HennesRupak MajumdarDebmalya MandalGoran RadanovicPublished in: CoRR (2023)
Keyphrases
- markov decision processes
- finite state
- dynamic programming
- state space
- reinforcement learning
- transition matrices
- optimal policy
- model based reinforcement learning
- reinforcement learning algorithms
- planning under uncertainty
- average reward
- average cost
- reachability analysis
- decision processes
- action space
- factored mdps
- finite horizon
- partially observable
- infinite horizon
- policy iteration
- risk sensitive
- markov decision process
- decision theoretic planning
- state and action spaces
- multi agent
- markov decision problems
- fixed point