Solving Partially Observable Stochastic Shortest-Path Games.
Petr TomásekKarel HorákAditya AradhyeBranislav BosanskýKrishnendu ChatterjeePublished in: IJCAI (2021)
Keyphrases
- markov decision problems
- partially observable
- stochastic shortest path
- markov decision processes
- state space
- reinforcement learning
- decision problems
- dynamical systems
- linear programming
- infinite horizon
- optimal policy
- belief state
- decision theoretic
- decision processes
- dynamic programming
- policy iteration
- utility function
- expected utility
- bayesian networks
- reinforcement learning algorithms
- decision making
- nash equilibrium
- transition probabilities
- planning domains
- influence diagrams
- computational complexity
- machine learning
- orders of magnitude
- sufficient conditions
- markov chain
- probabilistic model
- special case