Zobrazeno 1 - 10
of 86
pro vyhledávání: '"Eysenbach, Benjamin"'
Autor:
Bortkiewicz, Michał, Pałucki, Władek, Myers, Vivek, Dziarmaga, Tadeusz, Arczewski, Tomasz, Kuciński, Łukasz, Eysenbach, Benjamin
Self-supervision has the potential to transform reinforcement learning (RL), paralleling the breakthroughs it has enabled in other areas of machine learning. While self-supervised learning in other domains aims to find patterns in a fixed dataset, se
Externí odkaz:
http://arxiv.org/abs/2408.11052
In this paper, we present empirical evidence of skills and directed exploration emerging from a simple RL algorithm long before any successful trials are observed. For example, in a manipulation task, the agent is given a single observation of the go
Externí odkaz:
http://arxiv.org/abs/2408.05804
Temporal distances lie at the heart of many algorithms for planning, control, and reinforcement learning that involve reaching goals, allowing one to estimate the transit time between two states. However, prior attempts to define such temporal distan
Externí odkaz:
http://arxiv.org/abs/2406.17098
Publikováno v:
International Conference on Machine Learning, 2024
In supervised learning, understanding an input's proximity to the training data can help a model decide whether it has sufficient evidence for reaching a reliable prediction. While powerful probabilistic models such as Gaussian Processes naturally ha
Externí odkaz:
http://arxiv.org/abs/2406.10775
Given time series data, how can we answer questions like "what will happen in the future?" and "how did we get here?" These sorts of probabilistic inference questions are challenging when observations are high-dimensional. In this paper, we show how
Externí odkaz:
http://arxiv.org/abs/2403.04082
Some reinforcement learning (RL) algorithms can stitch pieces of experience to solve a task never seen before during training. This oft-sought property is one of the few ways in which RL methods based on dynamic-programming differ from RL methods bas
Externí odkaz:
http://arxiv.org/abs/2401.11237
Autor:
Ni, Tianwei, Eysenbach, Benjamin, Seyedsalehi, Erfan, Ma, Michel, Gehring, Clement, Mahajan, Aditya, Bacon, Pierre-Luc
Representations are at the core of all deep reinforcement learning (RL) methods for both Markov decision processes (MDPs) and partially observable Markov decision processes (POMDPs). Many representation learning methods and theoretical frameworks hav
Externí odkaz:
http://arxiv.org/abs/2401.08898
Predicting and reasoning about the future lie at the heart of many time-series questions. For example, goal-conditioned reinforcement learning can be viewed as learning representations to predict which states are likely to be visited in the future. W
Externí odkaz:
http://arxiv.org/abs/2310.20141
Autor:
Hatch, Kyle, Eysenbach, Benjamin, Rafailov, Rafael, Yu, Tianhe, Salakhutdinov, Ruslan, Levine, Sergey, Finn, Chelsea
Publikováno v:
Proceedings of The 5th Annual Learning for Dynamics and Control Conference, PMLR 211:155-169, 2023
While many real-world problems that might benefit from reinforcement learning, these problems rarely fit into the MDP mold: interacting with the environment is often expensive and specifying reward functions is challenging. Motivated by these challen
Externí odkaz:
http://arxiv.org/abs/2307.13101
As with any machine learning problem with limited data, effective offline RL algorithms require careful regularization to avoid overfitting. One-step methods perform regularization by doing just a single step of policy improvement, while critic regul
Externí odkaz:
http://arxiv.org/abs/2307.12968