Sequential Halving for Partially Observable Games.
Tom PepelsTristan CazenaveMark H. M. WinandsPublished in: CGW/GIGA@IJCAI (2015)
Keyphrases
- partially observable
- state space
- dynamical systems
- reinforcement learning
- markov decision processes
- decision problems
- infinite horizon
- partial observability
- partial observations
- belief state
- markov decision problems
- partially observable environments
- random sampling
- action models
- game theory
- optimal policy
- markov chain
- state variables
- decision theoretic
- learning algorithm
- reward function
- optimal control
- nash equilibrium
- heuristic search
- orders of magnitude
- partially observable domains