Fetching the paper…
Reading the bibliography…
Deep reinforcement learning agents, trained on raw pixel inputs, often fail to generalize beyond their training environments, relying on spurious correlations and irrelevant background details.
A cognitive theory of consciousness
Bernard J Baars · 1993
Earlier work this paper cites.
The conscious access hypothesis: origins and recent evidence
Bernard J Baars · 2002
Earlier work this paper cites.
Two-frame motion estimation based on polynomial expansion
Gunnar Farnebäck · 2003
Earlier work this paper cites.
Bitboard methods for games
Cameron Browne · 2014
Earlier work this paper cites.
A distributional perspective on reinforcement learning
Marc G Bellemare, Will Dabney, and Rémi Munos · 2017
Earlier work this paper cites.
The consciousness prior, 2017
Yoshua Bengio · 2017
Earlier work this paper cites.
Generalization and regularization in dqn
Jesse Farebrother, Marlos C. Machado, and Michael Bowling · 2018
Cited alongside, same era.
Investigating simple object representations in model-free deep reinforcement learning
Guy Davidson and Brenden M. Lake · 2020
Cited alongside, same era.
Deep reinforcement learning at the edge of the statistical precipice
Rishabh Agarwal, Max Schwarzer, Pablo Samuel Castro, Aaron Courville, and Marc G Bellemare · 2021
Cited alongside, same era.
Relevance-guided modeling of object dynamics for reinforcement learning
William Agnew and Pedro Domingos · 2021
Cited alongside, same era.
A review for deep reinforcement learning in atari: Benchmarks, challenges, and solutions
Jiajun Fan · 2021
Cited alongside, same era.
Generalization and robustness implications in object-centric learning
Andrea Dittadi, Samuele S. Papa, Michele De Vita, Bernhard Schölkopf, Ole Winther, and Francesco Locatello · 2022
Later among the works it cites.
Boosting object representation learning via motion and object continuity
Quentin Delfosse, Wolfgang Stammer, Thomas Rothenbächer, Dwarak Vittal, and Kristian Kersting · 2023
Later among the works it cites.
An attentive approach for building partial reasoning agents from pixels
Safa Alver and Doina Precup · 2024
Later among the works it cites.
Representation matters for mastering chess: Improved feature representation in alphazero outperforms changing to transformers
Johannes Czech, Jannis Blüml, Kristian Kersting, and Hedinn Steingrimsson · 2024
Later among the works it cites.
Stop regressing: Training value functions via classification for scalable deep RL
Jesse Farebrother, Jordi Orbay, Quan Vuong, Adrien Ali Taïga, Yevgen Chebotar, Ted Xiao, Alex Irpan, Sergey Levine, Pablo Samuel Castro, Aleksandra Faust, Aviral Kumar, and Rishabh Agarwal · 2024
Later among the works it cites.
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
Look where you look! saliency-guided q-networks for generalization in visual reinforcement learning
David Bertoin, Adil Zouitine, Mehdi Zouitine, and Emmanuel Rachelson · 2022
Cited alongside, same era.
Hackatari: Atari learning environments for robust and continual reinforcement learning
Quentin Delfosse, Jannis Blüml, Bjarne Gregori, and Kristian Kersting
Cited in the paper.
OCAtari: Object-centric Atari 2600 reinforcement learning environments
Quentin Delfosse, Jannis Blüml, Bjarne Gregori, Sebastian Sztwiertnia, and Kristian Kersting
Cited in the paper.
Interpretable concept bottlenecks to align reinforcement learning agents
Quentin Delfosse, Sebastian Sztwiertnia, Mark Rothermel, Wolfgang Stammer, and Kristian Kersting
Cited in the paper.
Supplementary Materials
Cited in the paper.