Reinforcement Learning and Shaping: Encouraging Intended Behaviors.
Adam LaudGerald DeJongPublished in: ICML (2002)
Keyphrases
- reinforcement learning
- reward shaping
- real robot
- reinforcement learning algorithms
- function approximation
- state space
- optimal policy
- mobile robot
- temporal difference
- learning algorithm
- markov decision problems
- sensory inputs
- temporal difference learning
- state transitions
- autonomous learning
- machine learning
- policy iteration
- robotic control
- partially observable
- action selection
- finite state machines
- optimal control
- transfer learning
- monte carlo
- cooperative
- learning environment