Epidemiologically and Socio-economically Optimal Policies via Bayesian Optimization.
Amit ChandakDebojyoti DeyBhaskar MukhotyPurushottam KarPublished in: CoRR (2020)
Keyphrases
- optimal policy
- markov decision processes
- decision problems
- dynamic programming
- bayesian reinforcement learning
- reinforcement learning
- state space
- infinite horizon
- long run
- finite horizon
- average reward
- finite state
- multistage
- initial state
- markov decision process
- state dependent
- average reward reinforcement learning
- dynamic programming algorithms
- sufficient conditions
- data mining
- serial inventory systems
- bayesian networks
- control policies
- partially observable markov decision processes
- average cost
- monte carlo