Is Vanilla Policy Gradient Overlooked? Analyzing Deep Reinforcement Learning for Hanabi.
Bram GrootenJelle WemmenhoveMaurice PootJim PortegiesPublished in: CoRR (2022)
Keyphrases
- policy gradient
- reinforcement learning
- actor critic
- function approximation
- policy search
- reinforcement learning algorithms
- model free reinforcement learning
- policy gradient methods
- gradient method
- optimal control
- markov decision processes
- average reward
- temporal difference
- model free
- partially observable markov decision processes
- function approximators
- state action
- reinforcement learning methods
- optimal policy
- state space
- dynamic programming
- machine learning
- learning algorithm