Stateful Posted Pricing with Vanishing Regret via Dynamic Deterministic Markov Decision Processes.
Yuval EmekRon LaviRad NiazadehYangguang ShiPublished in: Math. Oper. Res. (2024)
Keyphrases
- markov decision processes
- reward function
- state space
- optimal policy
- total reward
- finite state
- reinforcement learning
- policy iteration
- transition matrices
- dynamic programming
- decision processes
- planning under uncertainty
- expected reward
- partially observable
- reachability analysis
- infinite horizon
- factored mdps
- decision theoretic planning
- risk sensitive
- average cost
- model based reinforcement learning
- action sets
- average reward
- markov decision process
- stationary policies
- finite horizon
- state abstraction
- reinforcement learning algorithms
- lower bound
- dynamic environments
- optimal control
- learning algorithm