1 code implementation • 25 Oct 2022 • Roberto Gallotta, Kai Arulkumaran, L. B. Soros
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.
1 code implementation • 12 May 2022 • Roberto Gallotta, Kai Arulkumaran, L. B. Soros
When generating content for video games using procedural content generation (PCG), the goal is to create functional assets of high quality.
no code implementations • 24 Mar 2022 • Arthur Juliani, Kai Arulkumaran, Shuntaro Sasai, Ryota Kanai
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.
1 code implementation • 24 Feb 2022 • Kai Arulkumaran, Dylan R. Ashley, Jürgen Schmidhuber, Rupesh K. Srivastava
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.
no code implementations • 23 Feb 2022 • Dylan R. Ashley, Kai Arulkumaran, Jürgen Schmidhuber, Rupesh Kumar Srivastava
Lately, there has been a resurgence of interest in using supervised learning to solve reinforcement learning problems.
1 code implementation • 17 Aug 2021 • Tianhong Dai, Hengyan Liu, Kai Arulkumaran, Guangyu Ren, Anil Anthony Bharath
We evaluate DTGSH on five challenging robotic manipulation tasks in simulated robot environments, where we show that our method can learn more quickly and reach higher performance than other state-of-the-art approaches on all tasks.
1 code implementation • 4 Aug 2021 • Kai Arulkumaran, Dan Ogawa Lillrank
The introduction of the generative adversarial imitation learning (GAIL) algorithm has spurred the development of scalable imitation learning approaches using deep neural networks.
no code implementations • 19 May 2020 • Pierre-Alexandre Kamienny, Kai Arulkumaran, Feryal Behbahani, Wendelin Boehmer, Shimon Whiteson
Using privileged information during training can improve the sample efficiency and performance of machine learning systems.
no code implementations • 18 Dec 2019 • Tianhong Dai, Kai Arulkumaran, Tamara Gerbert, Samyakh Tukra, Feryal Behbahani, Anil Anthony Bharath
Furthermore, even with an improved saliency method introduced in this work, we show that qualitative studies may not always correspond with quantitative measures, necessitating the combination of inspection tools in order to provide sufficient insights into the behaviour of trained agents.
1 code implementation • 21 Nov 2019 • Andrea Agostinelli, Kai Arulkumaran, Marta Sarrico, Pierre Richemond, Anil Anthony Bharath
Recently, neuro-inspired episodic control (EC) methods have been developed to overcome the data-inefficiency of standard deep reinforcement learning approaches.
1 code implementation • 21 Nov 2019 • Marta Sarrico, Kai Arulkumaran, Andrea Agostinelli, Pierre Richemond, Anil Anthony Bharath
Deep networks have enabled reinforcement learning to scale to more complex and challenging domains, but these methods typically require large quantities of training data.
1 code implementation • 5 Feb 2019 • Kai Arulkumaran, Antoine Cully, Julian Togelius
In January 2019, DeepMind revealed AlphaStar to the world-the first artificial intelligence (AI) system to beat a professional player at the game of StarCraft II-representing a milestone in the progress of AI.
1 code implementation • ICLR 2019 • Ryutaro Tanno, Kai Arulkumaran, Daniel C. Alexander, Antonio Criminisi, Aditya Nori
Deep neural networks and decision trees operate on largely separate paradigms; typically, the former performs representation learning with pre-specified architectures, while the latter is characterised by learning hierarchies over pre-specified features with data-driven architectures.
no code implementations • 23 May 2018 • Sebastian Tschiatschek, Kai Arulkumaran, Jan Stühmer, Katja Hofmann
In this paper we propose DELIP, an approach to model learning for POMDPs that utilizes amortized structured variational inference.
2 code implementations • 19 Oct 2017 • Antonia Creswell, Tom White, Vincent Dumoulin, Kai Arulkumaran, Biswa Sengupta, Anil A. Bharath
Generative adversarial networks (GANs) provide a way to learn deep representations without extensively annotated training data.
no code implementations • 28 Aug 2017 • Antonia Creswell, Kai Arulkumaran, Anil A. Bharath
When training autoencoders on image data a natural choice of loss function is BCE, since pixel values may be normalised to take values in [0, 1] and the decoder model may be designed to generate samples that take values in (0, 1).
no code implementations • 19 Aug 2017 • Kai Arulkumaran, Marc Peter Deisenroth, Miles Brundage, Anil Anthony Bharath
Deep reinforcement learning is poised to revolutionise the field of AI and represents a step towards building autonomous systems with a higher level understanding of the visual world.
3 code implementations • 8 Nov 2016 • Nat Dilokthanakul, Pedro A. M. Mediano, Marta Garnelo, Matthew C. H. Lee, Hugh Salimbeni, Kai Arulkumaran, Murray Shanahan
We study a variant of the variational autoencoder model (VAE) with a Gaussian mixture as a prior distribution, with the goal of performing unsupervised clustering through deep generative models.
Ranked #7 on Human Pose Forecasting on HumanEva-I
1 code implementation • 28 Oct 2016 • Antonia Creswell, Kai Arulkumaran, Anil Anthony Bharath
Generative autoencoders are those which are trained to softly enforce a prior on the latent distribution learned by the inference model.
no code implementations • 18 Sep 2016 • Marta Garnelo, Kai Arulkumaran, Murray Shanahan
Deep reinforcement learning (DRL) brings the power of deep neural networks to bear on the generic task of trial-and-error learning, and its effectiveness has been convincingly demonstrated on tasks such as Atari video games and the game of Go.
no code implementations • 27 Apr 2016 • Kai Arulkumaran, Nat Dilokthanakul, Murray Shanahan, Anil Anthony Bharath
In this paper we combine one method for hierarchical reinforcement learning - the options framework - with deep Q-networks (DQNs) through the use of different "option heads" on the policy network, and a supervisory network for choosing between the different options.
Hierarchical Reinforcement Learning reinforcement-learning +1