Výsledky vyhledávání - "Liarokapis, Minas"

Report

Benchmarking Reinforcement Learning Methods for Dexterous Robotic Manipulation with a Three-Fingered Gripper

Autor: Cutler, Elizabeth, Xing, Yuning, Cui, Tony, Zhou, Brendan, van Rijnsoever, Koen, Hart, Ben, Valencia, David, Ong, Lee Violet C., Gee, Trevor, Liarokapis, Minas, Williams, Henry

Publikováno v: Australasian conference on robotics and automation (ACRA 2023)

Reinforcement Learning (RL) training is predominantly conducted in cost-effective and controlled simulation environments. However, the transfer of these trained models to real-world tasks often presents unavoidable challenges. This research explores

Externí odkaz: http://arxiv.org/abs/2408.14747

Zobrazit plný text záznamu

Report

Image-Based Deep Reinforcement Learning with Intrinsically Motivated Stimuli: On the Execution of Complex Robotic Tasks

Autor: Valencia, David, Williams, Henry, Xing, Yuning, Gee, Trevor, Liarokapis, Minas, MacDonald, Bruce A.

Reinforcement Learning (RL) has been widely used to solve tasks where the environment consistently provides a dense reward value. However, in real-world scenarios, rewards can often be poorly defined or sparse. Auxiliary signals are indispensable for

Externí odkaz: http://arxiv.org/abs/2407.21338

Zobrazit plný text záznamu

Report

CTD4 -- A Deep Continuous Distributional Actor-Critic Agent with a Kalman Fusion of Multiple Critics

Autor: Valencia, David, Williams, Henry, Gee, Trevor, MacDonald, Bruce A, Liarokapis, Minas

Categorical Distributional Reinforcement Learning (CDRL) has demonstrated superior sample efficiency in learning complex tasks compared to conventional Reinforcement Learning (RL) approaches. However, the practical application of CDRL is encumbered b

Externí odkaz: http://arxiv.org/abs/2405.02576

Zobrazit plný text záznamu