Inferring the Optimal Policy using Markov Chain Monte Carlo.
Brandon TrabuccoAlbert QuSimon LiGaneshkumar AshokavardhananPublished in: CoRR (2019)
Keyphrases
- optimal policy
- markov decision processes
- dynamic programming
- state space
- reinforcement learning
- decision problems
- finite state
- long run
- infinite horizon
- state dependent
- finite horizon
- multistage
- bayesian reinforcement learning
- markov decision process
- average reward
- policy iteration
- average cost
- control policies
- sufficient conditions
- asymptotically optimal
- lost sales
- partially observable markov decision processes