Finite-Time Error Analysis of Soft Q-Learning: Switching System Approach.
Narim JeongDonghwan LeePublished in: CoRR (2024)
Keyphrases
- error analysis
- least squares
- cooperative
- reinforcement learning
- state space
- learning algorithm
- error correction
- function approximation
- cross ratio
- multi agent
- reinforcement learning algorithms
- optimal policy
- markov decision processes
- finite number
- model free
- learning rate
- multi agent reinforcement learning
- multi agent systems
- stochastic approximation
- potential field