Settling Constant Regrets in Linear Markov Decision Processes.
Weitong ZhangZhiyuan FanJiafan HeQuanquan GuPublished in: CoRR (2024)
Keyphrases
- markov decision processes
- optimal policy
- state space
- finite state
- transition matrices
- policy iteration
- reinforcement learning
- dynamic programming
- reachability analysis
- finite horizon
- planning under uncertainty
- partially observable
- markov decision process
- average reward
- infinite horizon
- reinforcement learning algorithms
- average cost
- action sets
- decision theoretic planning
- risk sensitive
- stationary policies
- factored mdps
- decision processes
- state and action spaces
- model based reinforcement learning
- data mining
- decision diagrams
- markov decision problems
- total reward
- initial state
- semi markov decision processes