Long-Term Exploration in Persistent MDPs.
Leonid UgadiarovAlexey SkrynnikAleksandr I. PanovPublished in: MICAI (1) (2021)
Keyphrases
- long term
- markov decision processes
- model based reinforcement learning
- short term
- reinforcement learning
- state space
- average cost
- genetic algorithm
- medium term
- planning under uncertainty
- finite horizon
- search strategies
- dynamic programming
- optimal policy
- markov decision problems
- linear programming
- information visualization
- optimal solution
- decision processes
- decision theoretic planning
- active exploration
- markov chain