Independent Policy Gradient Methods for Competitive Reinforcement Learning.
Constantinos DaskalakisDylan J. FosterNoah GolowichPublished in: NeurIPS (2020)
Keyphrases
- policy gradient methods
- reinforcement learning
- natural actor critic
- policy gradient
- actor critic
- function approximation
- robot arm
- reinforcement learning algorithms
- reinforcement learning problems
- state space
- transfer learning
- function approximators
- dynamic programming
- belief revision
- temporal difference
- reinforcement learning methods