Keyphrases
- action selection
- reinforcement learning
- continuous state and action spaces
- markov decision processes
- heuristic search
- action space
- state space
- monte carlo
- robot soccer
- basal ganglia
- general game playing
- temporal difference
- evaluation function
- optimal policy
- function approximation
- factored mdps
- decision making
- uct algorithm
- multi agent
- policy iteration
- human robot
- action selection mechanism
- alpha beta
- belief state
- search methods
- heuristic search algorithms
- partially observable
- reinforcement learning algorithms
- markov decision problems
- model free
- search algorithm
- learning algorithm
- finite horizon
- function approximators
- total reward
- dynamic programming