Weight Clipping for Deep Continual and Reinforcement Learning.
Mohamed ElsayedQingfeng LanClare LyleA. Rupam MahmoodPublished in: CoRR (2024)
Keyphrases
- reinforcement learning
- function approximation
- dynamic programming
- state space
- optimal policy
- markov decision processes
- weight assignment
- deep learning
- reinforcement learning algorithms
- model free
- learning algorithm
- policy search
- machine learning
- action selection
- supervised learning
- learning classifier systems
- weighting scheme
- multi agent
- learning capabilities
- feature selection
- action space
- social networks
- relational reinforcement learning
- data sets
- robotic control