An Architecture for Distinguishing between Predictors and Inhibitors in Reinforcement Learning.
Patrick C. ConnorThomas P. TrappenbergPublished in: ICLR (Workshop Poster) (2014)
Keyphrases
- reinforcement learning
- reinforcement learning algorithms
- function approximation
- model free
- stochastic approximation
- temporal difference
- state space
- supervised learning
- direct policy search
- real time
- robot control
- control problems
- learning problems
- objective function
- learning algorithm
- machine learning
- transfer learning
- learning environment
- reward function
- multi agent
- learning capabilities
- action space
- temporal difference learning
- reinforcement learning methods
- transition model
- policy search
- wet lab
- real world