Horizon-Free Regret for Linear Markov Decision Processes.
Zihan ZhangJason D. LeeYuxin ChenSimon S. DuPublished in: CoRR (2024)
Keyphrases
- markov decision processes
- total reward
- reward function
- optimal policy
- finite state
- state space
- policy iteration
- dynamic programming
- reinforcement learning algorithms
- planning under uncertainty
- expected reward
- decision processes
- average reward
- reachability analysis
- model based reinforcement learning
- factored mdps
- decision theoretic planning
- discount factor
- transition matrices
- infinite horizon
- markov decision process
- action sets
- finite horizon
- action space
- reinforcement learning
- partially observable
- state abstraction
- regret bounds
- average cost
- loss function
- lower bound
- optimal solution
- risk sensitive
- multi agent