Loss of Plasticity in Continual Deep Reinforcement Learning.
Zaheer AbbasRosie ZhaoJoseph ModayilAdam WhiteMarlos C. MachadoPublished in: CoLLAs (2023)
Keyphrases
- reinforcement learning
- multi agent
- machine learning
- state space
- model free
- optimal policy
- learning algorithm
- function approximation
- learning process
- markov decision processes
- neural network model
- data sets
- robotic control
- reinforcement learning algorithms
- learning mechanism
- biologically inspired
- decision making
- feed forward
- optimal control
- learning problems
- learning classifier systems
- supervised learning
- temporal difference
- lower bound
- multi agent reinforcement learning
- real time