no code implementations • 5 Sep 2022 • Sasha Salter, Markus Wulfmeier, Dhruva Tirumala, Nicolas Heess, Martin Riedmiller, Raia Hadsell, Dushyant Rao
The ability to discover useful behaviours from past experience and transfer them to new tasks is considered a core component of natural embodied intelligence.
no code implementations • 20 Jan 2022 • Sasha Salter, Kristian Hartikainen, Walter Goodwin, Ingmar Posner
Key to these fields is the use of information asymmetry across architectural modules to bias which skills are learnt.
no code implementations • 19 Nov 2019 • Sasha Salter, Dushyant Rao, Markus Wulfmeier, Raia Hadsell, Ingmar Posner
Image-based Reinforcement Learning is known to suffer from poor sample efficiency and generalisation to unseen visuals such as distractors (task-independent aspects of the observation space).
no code implementations • 30 Sep 2019 • Yizhe Wu, Sudhanshu Kasewa, Oliver Groth, Sasha Salter, Li Sun, Oiwi Parker Jones, Ingmar Posner
In this paper we explore the richness of information captured by the latent space of a vision-based generative model.
no code implementations • 25 Sep 2019 • Sasha Salter, Dushyant Rao, Markus Wulfmeier, Raia Hadsell, Ingmar Posner
Applying reinforcement learning (RL) to physical systems presents notable challenges, given requirements regarding sample efficiency, safety, and physical constraints compared to simulated environments.
no code implementations • 25 Sep 2019 • Yizhe Wu, Sudhanshu Kasewa, Oliver Groth, Sasha Salter, Li Sun, Oiwi Parker Jones, Ingmar Posner
In this paper we investigate an artificial agent's ability to perform task-focused tool synthesis via imagination.
1 code implementation • ICML 2018 • Kyriacos Shiarlis, Markus Wulfmeier, Sasha Salter, Shimon Whiteson, Ingmar Posner
Many advanced Learning from Demonstration (LfD) methods consider the decomposition of complex, real-world tasks into simpler sub-tasks.