Interval Estimation for Reinforcement-Learning Algorithms in Continuous-State Domains.
Martha WhiteAdam M. WhitePublished in: NIPS (2010)
Keyphrases
- continuous state
- reinforcement learning algorithms
- reinforcement learning
- interval estimation
- markov decision processes
- policy search
- finite state
- action space
- state space
- model free
- transfer learning
- function approximation
- optimal policy
- dynamic programming
- partially observable markov decision processes
- control policies
- learning algorithm
- robot navigation
- reward function
- temporal difference
- stochastic games
- planning problems
- policy iteration
- neural network
- partially observable
- action selection
- function approximators
- average reward
- decision making