Zobrazeno 1 - 10
of 115
pro vyhledávání: '"Leal, Pablo P."'
Trading markets represent a real-world financial application to deploy reinforcement learning agents, however, they carry hard fundamental challenges such as high variance and costly exploration. Moreover, markets are inherently a multiagent domain c
Externí odkaz:
http://arxiv.org/abs/2107.08083
Deep Reinforcement Learning (DRL) has recently achieved significant advances in various domains. However, explaining the policy of RL agents still remains an open problem due to several factors, one being the complexity of explaining neural networks
Externí odkaz:
http://arxiv.org/abs/2011.07553
Predictive auxiliary tasks have been shown to improve performance in numerous reinforcement learning works, however, this effect is still not well understood. The primary purpose of the work presented here is to investigate the impact that an auxilia
Externí odkaz:
http://arxiv.org/abs/2004.00600
How to best explore in domains with sparse, delayed, and deceptive rewards is an important open problem for reinforcement learning (RL). This paper considers one such domain, the recently-proposed multi-agent benchmark of Pommerman. This domain is ve
Externí odkaz:
http://arxiv.org/abs/1907.11788
Deep reinforcement learning has achieved great successes in recent years, however, one main challenge is the sample inefficiency. In this paper, we focus on how to use action guidance by means of a non-expert demonstrator to improve sample efficiency
Externí odkaz:
http://arxiv.org/abs/1907.11703
Deep reinforcement learning has achieved great successes in recent years, but there are still open challenges, such as convergence to locally optimal policies and sample inefficiency. In this paper, we contribute a novel self-supervised auxiliary tas
Externí odkaz:
http://arxiv.org/abs/1907.10827
In this paper we explore how actor-critic methods in deep reinforcement learning, in particular Asynchronous Advantage Actor-Critic (A3C), can be extended with agent modeling. Inspired by recent works on representation learning and multiagent deep re
Externí odkaz:
http://arxiv.org/abs/1907.09597
The Pommerman Team Environment is a recently proposed benchmark which involves a multi-agent domain with challenges such as partial observability, decentralized execution (without communication), and very sparse and delayed rewards. The inaugural Pom
Externí odkaz:
http://arxiv.org/abs/1905.01360
Safe reinforcement learning has many variants and it is still an open research problem. Here, we focus on how to use action guidance by means of a non-expert demonstrator to avoid catastrophic events in a domain with sparse, delayed, and deceptive re
Externí odkaz:
http://arxiv.org/abs/1904.05759
Autor:
Vellojin, Jurleys P., Mardones, Jorge I., Vargas, Valentina, Leal, Pablo P., Corredor-Acosta, Andrea, Iriarte, José L.
Publikováno v:
In Progress in Oceanography February 2023 211
