Zobrazeno 1 - 10
of 100
pro vyhledávání: '"Lamb, Alex"'
Autor:
Tomar, Manan, Hansen-Estruch, Philippe, Bachman, Philip, Lamb, Alex, Langford, John, Taylor, Matthew E., Levine, Sergey
We introduce a new family of video prediction models designed to support downstream control tasks. We call these models Video Occupancy models (VOCs). VOCs operate in a compact latent space, thus avoiding the need to make predictions about individual
Externí odkaz:
http://arxiv.org/abs/2407.09533
Discovering an informative, or agent-centric, state representation that encodes only the relevant information while discarding the irrelevant is a key challenge towards scaling reinforcement learning algorithms and efficiently applying them to downst
Externí odkaz:
http://arxiv.org/abs/2404.14552
We study pre-training representations for decision-making using video data, which is abundantly available for tasks such as game agents and software testing. Even though significant empirical advances have been made on this problem, a theoretical und
Externí odkaz:
http://arxiv.org/abs/2403.13765
Autor:
Wang, Haonan, Zou, James, Mozer, Michael, Goyal, Anirudh, Lamb, Alex, Zhang, Linjun, Su, Weijie J, Deng, Zhun, Xie, Michael Qizhe, Brown, Hannah, Kawaguchi, Kenji
Creativity serves as a cornerstone for societal progress and innovation. With the rise of advanced generative AI models capable of tasks once reserved for human creativity, the study of AI's creative potential becomes imperative for its responsible d
Externí odkaz:
http://arxiv.org/abs/2401.01623
Autor:
Koul, Anurag, Sujit, Shivakanth, Chen, Shaoru, Evans, Ben, Wu, Lili, Xu, Byron, Chari, Rajan, Islam, Riashat, Seraj, Raihan, Efroni, Yonathan, Molu, Lekan, Dudik, Miro, Langford, John, Lamb, Alex
Goal-conditioned planning benefits from learned low-dimensional representations of rich observations. While compact latent representations typically learned from variational autoencoders or inverse dynamics enable goal-conditioned decision making, th
Externí odkaz:
http://arxiv.org/abs/2311.03534
Self-Supervised Learning (SSL) methods operate on unlabeled data to learn robust representations useful for downstream tasks. Most SSL methods rely on augmentations obtained by transforming the 2D image pixel map. These augmentations ignore the fact
Externí odkaz:
http://arxiv.org/abs/2301.11790
Autor:
Islam, Riashat, Zang, Hongyu, Tomar, Manan, Didolkar, Aniket, Islam, Md Mofijul, Arnob, Samin Yeasar, Iqbal, Tariq, Li, Xin, Goyal, Anirudh, Heess, Nicolas, Lamb, Alex
Several self-supervised representation learning methods have been proposed for reinforcement learning (RL) with rich observations. For real-world applications of RL, recovering underlying latent states is crucial, particularly when sensory inputs con
Externí odkaz:
http://arxiv.org/abs/2212.13835
Autor:
Tang, Shengpu, Frujeri, Felipe Vieira, Misra, Dipendra, Lamb, Alex, Langford, John, Mineiro, Paul, Kochman, Sebastian
Modern decision-making systems, from robots to web recommendation engines, are expected to adapt: to user preferences, changing circumstances or even new tasks. Yet, it is still uncommon to deploy a dynamically learning agent (rather than a fixed pol
Externí odkaz:
http://arxiv.org/abs/2211.07614
Models that can actively seek out the best quality training data hold the promise of more accurate, adaptable, and efficient machine learning. Active learning techniques often tend to prefer examples that are the most difficult to classify. While thi
Externí odkaz:
http://arxiv.org/abs/2211.00928
Autor:
Islam, Riashat, Zang, Hongyu, Goyal, Anirudh, Lamb, Alex, Kawaguchi, Kenji, Li, Xin, Laroche, Romain, Bengio, Yoshua, Combes, Remi Tachet Des
Goal-conditioned reinforcement learning (RL) is a promising direction for training agents that are capable of solving multiple tasks and reach a diverse set of objectives. How to \textit{specify} and \textit{ground} these goals in such a way that we
Externí odkaz:
http://arxiv.org/abs/2211.00247