Zobrazeno 1 - 10
of 56
pro vyhledávání: '"Arulkumaran, Kai"'
Autor:
Sato, Motoshige, Tomeoka, Kenichi, Horiguchi, Ilya, Arulkumaran, Kai, Kanai, Ryota, Sasai, Shuntaro
Brain-computer interfaces (BCIs) hold great potential for aiding individuals with speech impairments. Utilizing electroencephalography (EEG) to decode speech is particularly promising due to its non-invasive nature. However, recordings are typically
Externí odkaz:
http://arxiv.org/abs/2407.07595
In mixed-initiative co-creation tasks, wherein a human and a machine jointly create items, it is important to provide multiple relevant suggestions to the designer. Quality-diversity algorithms are commonly used for this purpose, as they can provide
Externí odkaz:
http://arxiv.org/abs/2210.13839
When generating content for video games using procedural content generation (PCG), the goal is to create functional assets of high quality. Prior work has commonly leveraged the feasible-infeasible two-population (FI-2Pop) constrained optimisation al
Externí odkaz:
http://arxiv.org/abs/2205.05834
In popular media, there is often a connection drawn between the advent of awareness in artificial agents and those same agents simultaneously achieving human or superhuman level intelligence. In this work, we explore the validity and potential applic
Externí odkaz:
http://arxiv.org/abs/2204.05133
Upside down reinforcement learning (UDRL) flips the conventional use of the return in the objective function in RL upside down, by taking returns as input and predicting actions. UDRL is based purely on supervised learning, and bypasses some prominen
Externí odkaz:
http://arxiv.org/abs/2202.11960
Lately, there has been a resurgence of interest in using supervised learning to solve reinforcement learning problems. Recent work in this area has largely focused on learning command-conditioned policies. We investigate the potential of one such met
Externí odkaz:
http://arxiv.org/abs/2202.12742
Hindsight experience replay (HER) is a goal relabelling technique typically used with off-policy deep reinforcement learning algorithms to solve goal-oriented tasks; it is well suited to robotic manipulation tasks that deliver only sparse rewards. In
Externí odkaz:
http://arxiv.org/abs/2108.07887
Autor:
Arulkumaran, Kai, Lillrank, Dan Ogawa
The introduction of the generative adversarial imitation learning (GAIL) algorithm has spurred the development of scalable imitation learning approaches using deep neural networks. Many of the algorithms that followed used a similar procedure, combin
Externí odkaz:
http://arxiv.org/abs/2108.01867
Autor:
Kamienny, Pierre-Alexandre, Arulkumaran, Kai, Behbahani, Feryal, Boehmer, Wendelin, Whiteson, Shimon
Using privileged information during training can improve the sample efficiency and performance of machine learning systems. This paradigm has been applied to reinforcement learning (RL), primarily in the form of distillation or auxiliary tasks, and l
Externí odkaz:
http://arxiv.org/abs/2005.09220
Autor:
Dai, Tianhong, Arulkumaran, Kai, Gerbert, Tamara, Tukra, Samyakh, Behbahani, Feryal, Bharath, Anil Anthony
Deep reinforcement learning has the potential to train robots to perform complex tasks in the real world without requiring accurate models of the robot or its environment. A practical approach is to train agents in simulation, and then transfer them
Externí odkaz:
http://arxiv.org/abs/1912.08324