Momentum in Reinforcement Learning.
Nino VieillardBruno ScherrerOlivier PietquinMatthieu GeistPublished in: AISTATS (2020)
Keyphrases
- reinforcement learning
- function approximation
- state space
- learning rate
- reinforcement learning algorithms
- policy search
- learning algorithm
- markov decision processes
- model free
- machine learning
- action selection
- dynamic programming
- optimal policy
- temporal difference learning
- temporal difference
- continuous state
- multi agent reinforcement learning
- active exploration
- robotic control
- optimal control
- reinforcement learning methods
- database
- evolutionary algorithm
- learning process
- multi agent
- databases