Reinforcement Learning with Human Feedback in Mountain Car.
W. Bradley KnoxAdam Bradley SetapenPeter StonePublished in: AAAI Spring Symposium: Help Me Help You: Bridging the Gaps in Human-Agent Collaboration (2011)
Keyphrases
- mountain car
- reinforcement learning
- function approximation
- reinforcement learning methods
- direct policy search
- inverted pendulum
- state space
- markov decision processes
- dynamical systems
- optimal control
- model free
- temporal difference
- reinforcement learning algorithms
- dynamic programming
- machine learning
- optimal policy
- control strategies
- intelligent control
- function approximators
- learning process