Symmetric Reinforcement Learning Loss for Robust Learning on Diverse Tasks and Model Scales.
Ju-Seung ByunAndrew PerraultPublished in: CoRR (2024)
Keyphrases
- reinforcement learning
- adaptation process
- computational model
- prior knowledge
- learning process
- learning algorithm
- learning systems
- probabilistic model
- similarity measure
- mathematical model
- learning models
- learning scheme
- learning phase
- neural network
- supervised learning
- learning tasks
- learning problems
- decision theoretic
- learning mechanism
- complex domains