Independent Policy Gradient Methods for Competitive Reinforcement Learning.
Constantinos DaskalakisDylan J. FosterNoah GolowichPublished in: CoRR (2021)
Keyphrases
- policy gradient methods
- reinforcement learning
- natural actor critic
- policy gradient
- function approximation
- actor critic
- function approximators
- robot arm
- state space
- reinforcement learning problems
- optimal policy
- markov decision processes
- optimal control
- control problems
- learning algorithm
- temporal difference learning
- reinforcement learning algorithms
- reinforcement learning methods
- neural network
- search space
- machine learning