5k citations · 10.2k across the 28 of their papers we have counts for
28 papers
SIMA 2: A Generalist Embodied Agent for Virtual Worlds
SIMA team, Adrian Bolton, Alexander Lerchner +63
We introduce SIMA 2, a generalist embodied agent that understands and acts in a wide variety of 3D virtual worlds. Built upon a Gemini foundation model, SIMA 2 represents a signifi…
LMAct: A Benchmark for In-Context Imitation Learning with Long Multimodal Demonstrations
Anian Ruoss, Fabio Pardo, Harris Chan +3
In this paper, we present a benchmark to pressure-test today's frontier models' multimodal decision-making capabilities in the very long-context regime (up to one million tokens) a…
ElasticTok: Adaptive Tokenization for Image and Video
Wilson Yan, Volodymyr Mnih, Aleksandra Faust +3
Efficient video tokenization remains a key bottleneck in learning general purpose vision models that are capable of processing long video sequences. Prevailing approaches are restr…
Vision-Language Models as a Source of Rewards
Kate Baumli, Satinder Baveja, Feryal Behbahani +24
Building generalist agents that can accomplish many goals in rich open-ended environments is one of the research frontiers for reinforcement learning. A key limiting factor for bui…
In-context Reinforcement Learning with Algorithm Distillation
Michael Laskin, Luyu Wang, Junhyuk Oh +11
We propose Algorithm Distillation (AD), a method for distilling reinforcement learning (RL) algorithms into neural networks by modeling their training histories with a causal seque…
Palm up: Playing in the Latent Manifold for Unsupervised Pretraining
Hao Liu, Tom Zahavy, Volodymyr Mnih +1
Large and diverse datasets have been the cornerstones of many impressive advancements in artificial intelligence. Intelligent creatures, however, learn by interacting with the envi…
Wasserstein Distance Maximizing Intrinsic Control
Ishan Durugkar, Steven Hansen, Stephen Spencer +1
This paper deals with the problem of learning a skill-conditioned policy that acts meaningfully in the absence of a reward signal. Mutual information based objectives have shown so…
Discovering Diverse Nearly Optimal Policies with Successor Features
Tom Zahavy, Brendan O'Donoghue, Andre Barreto +3
Finding different solutions to the same problem is a key aspect of intelligence associated with creativity and adaptation to novel situations. In reinforcement learning, a set of d…
Relative Variational Intrinsic Control
Kate Baumli, David Warde-Farley, Steven Hansen +1
In the absence of external rewards, agents can still learn useful behaviors by identifying and mastering a set of diverse skills within their environment. Existing skill learning m…
Q-Learning in enormous action spaces via amortized approximate maximization
Tom Van de Wiele, David Warde-Farley, Andriy Mnih +1
Applying Q-learning to high-dimensional or continuous action spaces can be difficult due to the required maximization over the set of possible actions. Motivated by techniques from…
Unsupervised Learning of Object Keypoints for Perception and Control
Tejas Kulkarni, Ankush Gupta, Catalin Ionescu +4
The study of object representations in computer vision has primarily focused on developing representations that are useful for image classification, object detection, or semantic s…
Fast Task Inference with Variational Intrinsic Successor Features
Steven Hansen, Will Dabney, Andre Barreto +3
It has been established that diverse behaviors spanning the controllable subspace of an Markov decision process can be trained by rewarding a policy for being distinguishable from…
Unsupervised Control Through Non-Parametric Discriminative Rewards
David Warde-Farley, Tom Van de Wiele, Tejas Kulkarni +3
Learning to control an environment without hand-crafted rewards or expert data remains challenging and is at the frontier of reinforcement learning research. We present an unsuperv…
Learning by Playing - Solving Sparse Reward Tasks from Scratch
Martin Riedmiller, Roland Hafner, Thomas Lampe +6
We propose Scheduled Auxiliary Control (SAC-X), a new learning paradigm in the context of Reinforcement Learning (RL). SAC-X enables learning of complex behaviors - from scratch -…
IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
Lasse Espeholt, Hubert Soyer, Remi Munos +9
In this work we aim to solve a large collection of tasks using a single reinforcement learning agent with a single set of parameters. A key challenge is to handle the increased amo…
The Uncertainty Bellman Equation and Exploration
Brendan O'Donoghue, Ian Osband, Remi Munos +1
We consider the exploration/exploitation problem in reinforcement learning. For exploitation, it is well known that the Bellman equation connects the value at any time-step to the…
Reinforcement Learning with Unsupervised Auxiliary Tasks
Max Jaderberg, Volodymyr Mnih, Wojciech Marian Czarnecki +4
Deep reinforcement learning agents have achieved state-of-the-art results by directly maximising cumulative reward. However, environments contain a much wider variety of possible t…
Combining policy gradient and Q-learning
Brendan O'Donoghue, Remi Munos, Koray Kavukcuoglu +1
Policy gradient is an efficient technique for improving a policy in a reinforcement learning setting. However, vanilla online variants are on-policy only and not able to take advan…
Sample Efficient Actor-Critic with Experience Replay
Ziyu Wang, Victor Bapst, Nicolas Heess +4
This paper presents an actor-critic deep reinforcement learning agent with experience replay that is stable, sample efficient, and performs remarkably well on challenging environme…
Using Fast Weights to Attend to the Recent Past
Jimmy Ba, Geoffrey Hinton, Volodymyr Mnih +2
Until recently, research on artificial neural networks was largely restricted to systems with only two types of variable: Neural activities that represent the current or recent inp…
Strategic Attentive Writer for Learning Macro-Actions
Alexander, Vezhnevets, Volodymyr Mnih +5
We present a novel deep recurrent neural network architecture that learns to build implicit plans in an end-to-end manner by purely interacting with an environment in reinforcement…
Learning values across many orders of magnitude
Hado van Hasselt, Arthur Guez, Matteo Hessel +2
Most learning algorithms are not invariant to the scale of the function that is being approximated. We propose to adaptively normalize the targets used in learning. This is useful…
Asynchronous Methods for Deep Reinforcement Learning
Volodymyr Mnih, Adrià Puigdomènech Badia, Mehdi Mirza +5
We propose a conceptually simple and lightweight framework for deep reinforcement learning that uses asynchronous gradient descent for optimization of deep neural network controlle…
Policy Distillation
Andrei A. Rusu, Sergio Gomez Colmenarejo, Caglar Gulcehre +6
Policies for complex visual tasks have been successfully learned with deep reinforcement learning, using an approach called deep Q-networks (DQN), but relatively large (task-specif…