Login / Signup

Fine-tuning Reinforcement Learning Models is Secretly a Forgetting Mitigation Problem.

Maciej WolczykBartlomiej CupialMateusz OstaszewskiMichal BortkiewiczMichal ZajacRazvan PascanuLukasz KucinskiPiotr Milos
Published in: CoRR (2024)
Keyphrases
  • fine tuning
  • reinforcement learning
  • statistical models
  • experimental data
  • complex systems
  • real time
  • neural network
  • probability distribution
  • d objects
  • least squares
  • computational models
  • accurate models