On Neural Consolidation for Transfer in Reinforcement Learning. (arXiv:2210.02240v1 [cs.LG])

Although transfer learning is considered to be a milestone in deep
reinforcement learning, the mechanisms behind it are still poorly understood.
In particular, predicting if knowledge can be transferred between two given
tasks is still an unresolved problem. In this work, we explore the use of
network distillation as a feature extraction method to better understand the
context in which transfer can occur. Notably, we show that distillation does
not prevent knowledge transfer, including when transferring from multiple tasks
to …

arxiv consolidation reinforcement reinforcement learning transfer