Keyphrases
- action selection
- reinforcement learning
- continuous state and action spaces
- markov decision processes
- action space
- robot soccer
- monte carlo
- heuristic search
- state space
- basal ganglia
- factored mdps
- temporal difference
- decision making
- learning algorithm
- optimal policy
- human robot
- function approximation
- markov decision process
- machine learning
- finite horizon
- policy iteration
- markov decision problems
- partially observable
- evaluation function
- search algorithm
- reinforcement learning algorithms
- general game playing
- dynamic programming
- belief state
- uct algorithm
- neural network
- continuous state
- total reward
- action selection mechanism
- initial state
- average cost
- reward function
- infinite horizon
- finite state
- search methods
- dynamical systems
- multi agent