Zobrazeno 1 - 10
of 121
pro vyhledávání: '"Verma, Abhinav"'
Autor:
Shah, Ameesh, Voloshin, Cameron, Yang, Chenxi, Verma, Abhinav, Chaudhuri, Swarat, Seshia, Sanjit A.
Linear Temporal Logic (LTL) offers a precise means for constraining the behavior of reinforcement learning agents. However, in many tasks, LTL is insufficient for task specification; LTL-constrained policy optimization, where the goal is to optimize
Externí odkaz:
http://arxiv.org/abs/2404.11578
Autor:
Žikelić, Đorđe, Lechner, Mathias, Verma, Abhinav, Chatterjee, Krishnendu, Henzinger, Thomas A.
Reinforcement learning has shown promising results in learning neural network policies for complicated control tasks. However, the lack of formal guarantees about the behavior of such policies remains an impediment to their deployment. We propose a n
Externí odkaz:
http://arxiv.org/abs/2312.01456
Autor:
Verma, Abhinav, Nayak, Jogendra Kumar
Publikováno v:
Journal of Information, Communication and Ethics in Society, 2024, Vol. 22, Issue 2, pp. 256-274.
Externí odkaz:
http://www.emeraldinsight.com/doi/10.1108/JICES-05-2023-0073
Linear temporal logic (LTL) offers a simplified way of specifying tasks for policy optimization that may otherwise be difficult to describe with scalar reward functions. However, the standard RL framework can be too myopic to find maximally LTL satis
Externí odkaz:
http://arxiv.org/abs/2303.02135
Publikováno v:
In ISPRS Journal of Photogrammetry and Remote Sensing June 2024 212:289-305
We present Revel, a partially neural reinforcement learning (RL) framework for provably safe exploration in continuous state and action spaces. A key challenge for provably safe deep RL is that repeatedly verifying neural networks within a learning l
Externí odkaz:
http://arxiv.org/abs/2009.12612
We study the problem of learning differentiable functions expressed as programs in a domain-specific language. Such programmatic models can offer benefits such as composability and interpretability; however, learning them requires optimizing over a c
Externí odkaz:
http://arxiv.org/abs/2007.12101
Publikováno v:
In ISPRS Journal of Photogrammetry and Remote Sensing September 2023 203:55-70
We study the problem of programmatic reinforcement learning, in which policies are represented as short programs in a symbolic language. Programmatic policies can be more interpretable, generalizable, and amenable to formal verification than neural p
Externí odkaz:
http://arxiv.org/abs/1907.05431
Autor:
Cheng, Richard, Verma, Abhinav, Orosz, Gabor, Chaudhuri, Swarat, Yue, Yisong, Burdick, Joel W.
Dealing with high variance is a significant challenge in model-free reinforcement learning (RL). Existing methods are unreliable, exhibiting high variance in performance from run to run using different initializations/seeds. Focusing on problems aris
Externí odkaz:
http://arxiv.org/abs/1905.05380