Workshop summary: Results of the 2009 reinforcement learning competition.
David WingateCarlos DiukLihong LiMatthew TaylorJordan FrankPublished in: ICML (2009)
Keyphrases
- reinforcement learning
- function approximation
- state space
- multi agent
- learning algorithm
- markov decision processes
- reinforcement learning algorithms
- transfer learning
- monte carlo
- optimal policy
- dynamic programming
- learning capabilities
- video summarization
- selected papers
- robotic control
- transition model
- stochastic approximation
- reinforcement learning methods
- learning agents
- control policy
- reward function
- action selection
- model free
- learning problems
- supervised learning