Loss of Plasticity in Continual Deep Reinforcement Learning.
Zaheer AbbasRosie ZhaoJoseph ModayilAdam WhiteMarlos C. MachadoPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- function approximation
- markov decision processes
- learning mechanism
- model free
- biologically inspired
- neural network model
- machine learning
- reinforcement learning algorithms
- state space
- multi agent
- learning process
- learning algorithm
- multi agent reinforcement learning
- function approximators
- temporal difference learning
- optimal policy
- supervised learning
- policy search
- temporal difference
- genetic algorithm
- neural network
- robotic control
- autonomous learning
- reinforcement learning methods
- deep learning
- action selection
- optimal control
- transfer learning