Sketch-Based Linear Value Function Approximation.
Marc G. BellemareJoel VenessMichael BowlingPublished in: NIPS (2012)
Keyphrases
- linear value function approximation
- reinforcement learning
- linear programming
- reinforcement learning problems
- markov decision problems
- reinforcement learning algorithms
- markov games
- state space
- markov decision processes
- linear program
- np hard
- reinforcement learning methods
- control problems
- temporal difference
- policy iteration
- partially observable
- machine learning
- function approximation
- optimal policy
- function approximators
- control system
- learning algorithm