Zobrazeno 1 - 10
of 400
pro vyhledávání: '"Block, Adam"'
Autor:
Block, Adam B.
Many of the algorithms and theoretical results surrounding modern machine learning are predicated on the assumption that data are independent and identically distributed. Motivated by the numerous applications that do not satisfy this assumption, man
Externí odkaz:
https://hdl.handle.net/1721.1/155382
Imitation learning (IL) aims to mimic the behavior of an expert in a sequential decision making task by learning from demonstrations, and has been widely applied to robotics, autonomous driving, and autoregressive text generation. The simplest approa
Externí odkaz:
http://arxiv.org/abs/2407.15007
In order to circumvent statistical and computational hardness results in sequential decision-making, recent work has considered smoothed online learning, where the distribution of data at each time is assumed to have bounded likeliehood ratio with re
Externí odkaz:
http://arxiv.org/abs/2402.14987
Due to statistical lower bounds on the learnability of many function classes under privacy constraints, there has been recent interest in leveraging public data to improve the performance of private learning algorithms. In this model, algorithms must
Externí odkaz:
http://arxiv.org/abs/2402.09483
Publikováno v:
PASP 135 095003 (2023)
The Steward Observatory LEO Satellite Photometric Survey is a comprehensive observational survey to characterize the apparent brightness of the Starlink and OneWeb low Earth orbit satellites and evaluate the potential impact on astronomy. We report t
Externí odkaz:
http://arxiv.org/abs/2311.14092
This work studies training instabilities of behavior cloning with deep neural networks. We observe that minibatch SGD updates to the policy network during training result in sharp oscillations in long-horizon rewards, despite negligibly affecting the
Externí odkaz:
http://arxiv.org/abs/2310.11428
We propose a theoretical framework for studying behavior cloning of complex expert demonstrations using generative modeling. Our framework invokes low-level controllers - either learned or implicit in position-command control - to stabilize imitation
Externí odkaz:
http://arxiv.org/abs/2307.14619
A major challenge in reinforcement learning is to develop practical, sample-efficient algorithms for exploration in high-dimensional domains where generalization and function approximation is required. Low-Rank Markov Decision Processes -- where tran
Externí odkaz:
http://arxiv.org/abs/2307.03997
Smoothed online learning has emerged as a popular framework to mitigate the substantial loss in statistical and computational complexity that arises when one moves from classical to adversarial learning. Unfortunately, for some spaces, it has been sh
Externí odkaz:
http://arxiv.org/abs/2302.05430
Autor:
Block, Adam, Polyanskiy, Yury
Suppose we are given access to $n$ independent samples from distribution $\mu$ and we wish to output one of them with the goal of making the output distributed as close as possible to a target distribution $\nu$. In this work we show that the optimal
Externí odkaz:
http://arxiv.org/abs/2302.04658