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

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

5 February 2024

Bartłomiej Cupiał

Michal Bortkiewicz

Lukasz Kuciñski

Papers citing "Fine-tuning Reinforcement Learning Models is Secretly a Forgetting Mitigation Problem"

14 / 14 papers shown

Title
PaperBench: Evaluating AI's Ability to Replicate AI Research Giulio Starace Oliver Jaffe Dane Sherburn James Aung Jun Shern Chan ... Benjamin Kinsella Wyatt Thompson Johannes Heidecke Amelia Glaese Tejal Patwardhan ALM ELM 785 6 0 02 Apr 2025
Pretraining Generative Flow Networks with Inexpensive Rewards for Molecular Graph Generation Mohit Pandey G. Subbaraj Artem Cherkasov Martin Ester Emmanuel Bengio AI4CE 66 1 0 08 Mar 2025
BALROG: Benchmarking Agentic LLM and VLM Reasoning On Games Davide Paglieri Bartłomiej Cupiał Samuel Coward Ulyana Piterbarg Maciej Wolczyk ... Lerrel Pinto Rob Fergus Jakob Foerster Jack Parker-Holder Tim Rocktaschel LLMAG LRM 106 10 0 20 Nov 2024
The Joint Effect of Task Similarity and Overparameterization on Catastrophic Forgetting -- An Analytical Model Daniel Goldfarb Itay Evron Nir Weinberger Daniel Soudry Paul Hand 32 11 0 23 Jan 2024
Cal-QL: Calibrated Offline RL Pre-Training for Efficient Online Fine-Tuning Mitsuhiko Nakamoto Yuexiang Zhai Anika Singh Max Sobol Mark Yi-An Ma Chelsea Finn Aviral Kumar Sergey Levine OffRL OnRL 109 108 0 09 Mar 2023
Dungeons and Data: A Large-Scale NetHack Dataset Eric Hambro Roberta Raileanu Dan Rothermel Vegard Mella Tim Rocktaschel Heinrich Küttler Naila Murray OffRL 126 18 0 01 Nov 2022
Probing Transfer in Deep Reinforcement Learning without Task Engineering Andrei A. Rusu Sebastian Flennerhag Dushyant Rao Razvan Pascanu R. Hadsell 32 6 0 22 Oct 2022
Pre-Training for Robots: Offline RL Enables Learning New Tasks from a Handful of Trials Aviral Kumar Anika Singh F. Ebert Mitsuhiko Nakamoto Yanlai Yang Chelsea Finn Sergey Levine OffRL OnRL 123 64 0 11 Oct 2022
Disentangling Transfer in Continual Reinforcement Learning Maciej Wołczyk Michal Zajkac Razvan Pascanu Lukasz Kuciñski Piotr Milo's CLL 60 27 0 28 Sep 2022
Modular Lifelong Reinforcement Learning via Neural Composition Jorge Armando Mendez Mendez H. V. Seijen Eric Eaton OffRL KELM CLL 70 38 0 01 Jul 2022
Improving Intrinsic Exploration with Language Abstractions Jesse Mu Victor Zhong Roberta Raileanu Minqi Jiang Noah D. Goodman Tim Rocktaschel Edward Grefenstette 95 63 0 17 Feb 2022
Architecture Matters in Continual Learning Seyed Iman Mirzadeh Arslan Chaudhry Dong Yin Timothy Nguyen Razvan Pascanu Dilan Görür Mehrdad Farajtabar OOD KELM 109 58 0 01 Feb 2022
Offline Reinforcement Learning with Implicit Q-Learning Ilya Kostrikov Ashvin Nair Sergey Levine OffRL 212 832 0 12 Oct 2021
Decoupling Representation Learning from Reinforcement Learning Adam Stooke Kimin Lee Pieter Abbeel Michael Laskin SSL DRL 276 339 0 14 Sep 2020