Keyphrases
- reward shaping
- reinforcement learning
- reinforcement learning algorithms
- complex domains
- markov decision problems
- state space
- function approximation
- learning algorithm
- machine learning
- optimal policy
- linear programming
- model free
- temporal difference
- reward function
- least squares
- dynamic programming
- multi agent
- knowledge acquisition
- monte carlo
- partially observable
- continuous state
- policy search
- neural network