Prospect-theoretic Q-learning.
Vivek S. BorkarSiddharth ChandakPublished in: Syst. Control. Lett. (2021)
Keyphrases
- reinforcement learning
- function approximation
- cooperative
- multi agent
- state space
- learning algorithm
- reinforcement learning algorithms
- action selection
- model free
- stochastic approximation
- multi agent reinforcement learning
- optimal policy
- temporal difference learning
- learning rate
- bucket brigade
- temporal difference
- dynamic programming
- credit assignment
- continuous state spaces
- continuous state and action spaces
- markov decision processes
- hierarchical reinforcement learning
- potential field
- multiagent learning
- reinforcement learning methods
- single agent