Abstract Policy Evaluation for Reactive Agents.
Krysia BrodaChristopher J. HoggerPublished in: SARA (2005)
Keyphrases
- reactive agents
- policy evaluation
- reinforcement learning
- least squares
- temporal difference
- model free
- monte carlo
- policy iteration
- markov decision processes
- function approximation
- matrix inversion
- reinforcement learning algorithms
- variance reduction
- optimal policy
- artificial neural networks
- statistical inference
- semi parametric
- linear programming
- evaluation function
- supervised learning
- computational complexity
- image sequences