Reinforcement Learning with Trajectory Feedback.
Yonathan EfroniNadav MerlisShie MannorPublished in: AAAI (2021)
Keyphrases
- reinforcement learning
- function approximation
- state space
- trajectory data
- multi agent
- optimal policy
- markov decision processes
- robotic control
- relevance feedback
- learning algorithm
- model free
- reinforcement learning algorithms
- transfer learning
- data sets
- optimal control
- action selection
- machine learning
- feedback mechanisms
- dynamic programming
- markov decision process
- temporal difference learning
- stochastic approximation
- neural network