Zobrazeno 1 - 10
of 35
pro vyhledávání: '"Combes, Remi Tachet des"'
Autor:
Zang, Hongyu, Li, Xin, Zhang, Leiji, Liu, Yang, Sun, Baigui, Islam, Riashat, Combes, Remi Tachet des, Laroche, Romain
While bisimulation-based approaches hold promise for learning robust state representations for Reinforcement Learning (RL) tasks, their efficacy in offline RL tasks has not been up to par. In some instances, their performance has even significantly u
Externí odkaz:
http://arxiv.org/abs/2310.17139
Publikováno v:
Conference paper at ICLR 2023
Most offline reinforcement learning (RL) algorithms return a target policy maximizing a trade-off between (1) the expected performance gain over the behavior policy that collected the dataset, and (2) the risk stemming from the out-of-distribution-ne
Externí odkaz:
http://arxiv.org/abs/2306.13085
Autor:
Zang, Hongyu, Li, Xin, Yu, Jie, Liu, Chen, Islam, Riashat, Combes, Remi Tachet Des, Laroche, Romain
Offline reinforcement learning (RL) struggles in environments with rich and noisy inputs, where the agent only has access to a fixed dataset without environment interactions. Past works have proposed common workarounds based on the pre-training of st
Externí odkaz:
http://arxiv.org/abs/2211.00863
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
Autor:
Islam, Riashat, Tomar, Manan, Lamb, Alex, Efroni, Yonathan, Zang, Hongyu, Didolkar, Aniket, Misra, Dipendra, Li, Xin, van Seijen, Harm, Combes, Remi Tachet des, Langford, John
Learning to control an agent from data collected offline in a rich pixel-based visual observation space is vital for real-world applications of reinforcement learning (RL). A major challenge in this setting is the presence of input information that i
Externí odkaz:
http://arxiv.org/abs/2211.00164
Autor:
Dodge, Jesse, Prewitt, Taylor, Combes, Remi Tachet Des, Odmark, Erika, Schwartz, Roy, Strubell, Emma, Luccioni, Alexandra Sasha, Smith, Noah A., DeCario, Nicole, Buchanan, Will
By providing unprecedented access to computational resources, cloud computing has enabled rapid growth in technologies such as machine learning, the computational demands of which incur a high energy cost and a commensurate carbon footprint. As a res
Externí odkaz:
http://arxiv.org/abs/2206.05229
Most theoretically motivated work in the offline reinforcement learning setting requires precise uncertainty estimates. This requirement restricts the algorithms derived in that work to the tabular and linear settings where such estimates exist. In t
Externí odkaz:
http://arxiv.org/abs/2206.01085
A central object of study in Reinforcement Learning (RL) is the Markovian policy, in which an agent's actions are chosen from a memoryless probability distribution, conditioned only on its current state. The family of Markovian policies is broad enou
Externí odkaz:
http://arxiv.org/abs/2205.13950
Daniely and Schacham recently showed that gradient descent finds adversarial examples on random undercomplete two-layers ReLU neural networks. The term "undercomplete" refers to the fact that their proof only holds when the number of neurons is a van
Externí odkaz:
http://arxiv.org/abs/2104.03863
Attention is a powerful component of modern neural networks across a wide variety of domains. In this paper, we seek to quantify the regularity (i.e. the amount of smoothness) of the attention operation. To accomplish this goal, we propose a new math
Externí odkaz:
http://arxiv.org/abs/2102.05628