Zobrazeno 1 - 1
of 1
pro vyhledávání: '"Tilman Immisch"'
Publikováno v:
Frontiers in Neurorobotics, Vol 17 (2023)
Deep reinforcement learning (RL) agents often suffer from catastrophic forgetting, forgetting previously found solutions in parts of the input space when training new data. Replay memories are a common solution to the problem by decorrelating and shu
Externí odkaz:
https://doaj.org/article/cb93b1d707744a61b40c035d8d8d19e5
