Andrei A. Rusu

2 ta ish

Google DeepMind (United Kingdom)

1. Human-level control through deep reinforcement learning

   Volodymyr Mnih, Koray Kavukcuoglu, David Silver +16

   Maqola201510 iqtibos

   ABIABI:AkademIndex/2026.other.138991

2. Overcoming catastrophic forgetting in neural networks

   James Kirkpatrick, Razvan Pascanu, Neil C. Rabinowitz +11

   Maqola20173 iqtibos

   ABIABI:AkademIndex/2026.other.340410