A Theoretical Analysis of Optimistic Proximal Policy Optimization in Linear Markov Decision Processes.
Han ZhongTong ZhangPublished in: CoRR (2023)
Keyphrases
- markov decision processes
- theoretical analysis
- optimal policy
- policy iteration
- markov decision process
- finite horizon
- average reward
- average cost
- infinite horizon
- state space
- decision processes
- action space
- state and action spaces
- partially observable
- finite state
- reward function
- reinforcement learning
- dynamic programming
- policy evaluation
- transition matrices
- expected reward
- reachability analysis
- decision problems
- markov decision problems
- discounted reward
- total reward
- planning under uncertainty
- model based reinforcement learning
- factored mdps
- long run
- reinforcement learning algorithms
- multistage
- state dependent
- decision theoretic planning
- semi markov decision processes
- policy iteration algorithm
- control policies
- initial state
- temporal difference
- least squares
- state abstraction
- optimal solution