Reinforcement Learning with Trajectory Feedback.
Yonathan EfroniNadav MerlisShie MannorPublished in: CoRR (2020)
Keyphrases
- reinforcement learning
- function approximation
- state space
- learning algorithm
- multi agent
- model free
- relevance feedback
- multi agent reinforcement learning
- reinforcement learning algorithms
- machine learning
- optimal policy
- markov decision processes
- temporal difference learning
- action selection
- dynamic programming
- feedback mechanisms
- autonomous learning
- robotic control
- learning problems
- learning agent
- robot control
- temporal difference
- data sets
- case study
- neural network