Zobrazeno 1 - 10
of 2 315
pro vyhledávání: '"Eramo P"'
Autor:
Griesbach, Sebastian, D'Eramo, Carlo
Exploration is a crucial and distinctive aspect of reinforcement learning (RL) that remains a fundamental open problem. Several methods have been proposed to tackle this challenge. Commonly used methods inject random noise directly into the actions,
Externí odkaz:
http://arxiv.org/abs/2410.23840
Autor:
D'Eramo, Francesco, Lenoci, Alessandro
We investigate the cosmological consequences of axion interactions with standard model fermions accurately and precisely. Our analysis is entirely based on a phase space framework that allows us to keep track of the axion distribution in momentum spa
Externí odkaz:
http://arxiv.org/abs/2410.21253
Autor:
Watson, Joe, Song, Chen, Weeger, Oliver, Gruner, Theo, Le, An T., Hansel, Kay, Hendawy, Ahmed, Arenz, Oleg, Trojak, Will, Cranmer, Miles, D'Eramo, Carlo, Bülow, Fabian, Goyal, Tanmay, Peters, Jan, Hoffman, Martin W.
This survey examines the broad suite of methods and models for combining machine learning with physics knowledge for prediction and forecast, with a focus on partial differential equations. These methods have attracted significant interest due to the
Externí odkaz:
http://arxiv.org/abs/2408.09840
We explore the irreducible cosmological implications of a singlet real scalar field. Our focus is on theories with an approximate and spontaneously broken $\mathbb{Z}_2$ symmetry where quasi-stable domain walls can form at early times. This seemingly
Externí odkaz:
http://arxiv.org/abs/2407.19997
Deterministic policies are often preferred over stochastic ones when implemented on physical systems. They can prevent erratic and harmful behaviors while being easier to implement and interpret. However, in practice, exploration is largely performed
Externí odkaz:
http://arxiv.org/abs/2407.04864
Deep Reinforcement Learning (RL) is well known for being highly sensitive to hyperparameters, requiring practitioners substantial efforts to optimize them for the problem at hand. This also limits the applicability of RL in real-world scenarios. In r
Externí odkaz:
http://arxiv.org/abs/2405.16195
Autor:
Eramo, Romina, Salman, Hamzeh Eyal, Spezialetti, Matteo, Stern, Darko, Quinton, Pierre, Cicchetti, Antonio
The risen complexity of automotive systems requires new development strategies and methods to master the upcoming challenges. Traditional methods need thus to be changed by an increased level of automation, and a faster continuous improvement cycle.
Externí odkaz:
http://arxiv.org/abs/2404.02841
The vast majority of Reinforcement Learning methods is largely impacted by the computation effort and data requirements needed to obtain effective estimates of action-value functions, which in turn determine the quality of the overall performance and
Externí odkaz:
http://arxiv.org/abs/2403.02107
Autor:
Vincent, Théo, Metelli, Alberto Maria, Belousov, Boris, Peters, Jan, Restelli, Marcello, D'Eramo, Carlo
Approximate value iteration (AVI) is a family of algorithms for reinforcement learning (RL) that aims to obtain an approximation of the optimal value function. Generally, AVI algorithms implement an iterated procedure where each step consists of (i)
Externí odkaz:
http://arxiv.org/abs/2312.12869
Multi-goal robot manipulation tasks with sparse rewards are difficult for reinforcement learning (RL) algorithms due to the inefficiency in collecting successful experiences. Recent algorithms such as Hindsight Experience Replay (HER) expedite learni
Externí odkaz:
http://arxiv.org/abs/2312.02677