Abstract The combination of Reinforcement Learning (RL) with deep learning has led to a series of impressive feats, with many believing (deep) RL provides a path towards generally …
D Moriarty, A Schultz, J Grefenstette - Journal on Artificial Intelligence …, 1999 - Citeseer
This article characterizes the evolutionary algorithm approach to reinforcement learning in relation to the more standard, temporal di erence methods. We describe several research …
M Kiran, M Ozyildirim - arXiv preprint arXiv:2201.11182, 2022 - arxiv.org
Reinforcement learning (RL) applications, where an agent can simply learn optimal behaviors by interacting with the environment, are quickly gaining tremendous success in a …
MM Drugan - Swarm and evolutionary computation, 2019 - Elsevier
A variety of Reinforcement Learning (RL) techniques blends with one or more techniques from Evolutionary Computation (EC) resulting in hybrid methods classified according to their …
Y Zhang, L Li, W Wei, Y Lv, J Liang - Neural Networks, 2024 - Elsevier
In reinforcement learning, accurate estimation of the Q-value is crucial for acquiring an optimal policy. However, current successful Actor-Critic methods still suffer from …
Abstract Different from classic Supervised Learning, Reinforcement Learning (RL), is fundamentally interactive: an autonomous agent must learn how to behave in an unknown …
M Franceschetti, C Lacoux, R Ohouens, A Raffin… - arXiv preprint arXiv …, 2022 - arxiv.org
The SWIMMER environment is a standard benchmark in reinforcement learning (RL). In particular, it is often used in papers comparing or combining RL methods with direct policy …
A Dutech, T Edmunds, J Kok, M Lagoudakis… - Advances in Neural …, 2005 - Citeseer
It is widely agreed that the field of reinforcement learning would benefit from the establishment of standard benchmark problems and perhaps regular competitive events …
KO Stanley - Proceedings of the 14th annual conference companion …, 2012 - dl.acm.org
Neuroevolution, ie evolution of artificial neural networks, has recently emerged as a powerful technique for solving challenging reinforcement learning problems. Compared to …