Temporal Difference Learning with Compressed Updates: Error-Feedback meets Reinforcement Learning.
Aritra MitraGeorge J. PappasHamed HassaniPublished in: Trans. Mach. Learn. Res. (2024)
Keyphrases
- temporal difference learning
- reinforcement learning
- function approximation
- temporal difference
- fixed point
- evaluation function
- game playing
- reinforcement learning algorithms
- approximate value iteration
- markov decision process
- function approximators
- monte carlo
- multi agent
- optimal policy
- decision making
- labeled data
- learning tasks
- supervised learning
- state space
- active learning
- policy iteration
- learning algorithm
- neural network