Alchemy: A benchmark and analysis toolkit for meta-reinforcement learning agents

1 code implementation • 4 Feb 2021 • Jane X. Wang, Michael King, Nicolas Porcel, Zeb Kurth-Nelson, Tina Zhu, Charlie Deck, Peter Choy, Mary Cassin, Malcolm Reynolds, Francis Song, Gavin Buttimore, David P. Reichert, Neil Rabinowitz, Loic Matthey, Demis Hassabis, Alexander Lerchner, Matthew Botvinick

There has been rapidly growing interest in meta-learning as a method for increasing the flexibility and sample efficiency of reinforcement learning.

Meta-Learning Meta Reinforcement Learning +3

Automated curricula through setter-solver interactions

no code implementations • 27 Sep 2019 • Sebastien Racaniere, Andrew K. Lampinen, Adam Santoro, David P. Reichert, Vlad Firoiu, Timothy P. Lillicrap

We demonstrate the success of our approach in rich but sparsely rewarding 2D and 3D environments, where an agent is tasked to achieve a single goal selected from a set of possible goals that varies between episodes, and identify challenges for future work.

Learning and Querying Fast Generative Models for Reinforcement Learning

no code implementations • 8 Feb 2018 • Lars Buesing, Theophane Weber, Sebastien Racaniere, S. M. Ali Eslami, Danilo Rezende, David P. Reichert, Fabio Viola, Frederic Besse, Karol Gregor, Demis Hassabis, Daan Wierstra

A key challenge in model-based reinforcement learning (RL) is to synthesize computationally efficient and accurate environment models.

Atari Games Decision Making +3

Imagination-Augmented Agents for Deep Reinforcement Learning

2 code implementations • NeurIPS 2017 • Théophane Weber, Sébastien Racanière, David P. Reichert, Lars Buesing, Arthur Guez, Danilo Jimenez Rezende, Adria Puigdomènech Badia, Oriol Vinyals, Nicolas Heess, Yujia Li, Razvan Pascanu, Peter Battaglia, Demis Hassabis, David Silver, Daan Wierstra

We introduce Imagination-Augmented Agents (I2As), a novel architecture for deep reinforcement learning combining model-free and model-based aspects.

Model-based Reinforcement Learning reinforcement-learning +1

Neuronal Synchrony in Complex-Valued Deep Networks

no code implementations • 20 Dec 2013 • David P. Reichert, Thomas Serre

Here, we show how aspects of spike timing, long hypothesized to play a crucial role in cortical information processing, could be incorporated into deep networks to build richer, versatile representations.

Neuronal Adaptation for Sampling-Based Probabilistic Inference in Perceptual Bistability

no code implementations • NeurIPS 2011 • David P. Reichert, Peggy Series, Amos J. Storkey

Based on recent developments in machine learning, we show how neuronal adaptation can be understood as a mechanism that improves probabilistic, sampling-based inference.

Hallucinations in Charles Bonnet Syndrome Induced by Homeostasis: a Deep Boltzmann Machine Model

no code implementations • NeurIPS 2010 • Peggy Series, David P. Reichert, Amos J. Storkey

The Charles Bonnet Syndrome (CBS) is characterized by complex vivid visual hallucinations in people with, primarily, eye diseases and no other neurological pathology.