10.1k citations · 22.1k across the 78 of their papers we have counts for
17 papers · 1 filter
Composing Entropic Policies using Divergence Correction
Jonathan J Hunt, Andre Barreto, Timothy P Lillicrap +1
Composing previously mastered skills to solve novel tasks promises dramatic improvements in the data efficiency of reinforcement learning. Here, we analyze two recent works composi…
Learning Attractor Dynamics for Generative Memory
Yan Wu, Greg Wayne, Karol Gregor +1
A central challenge faced by memory systems is the robust retrieval of a stored pattern in the presence of interference due to other stored patterns and noise. A theoretically well…
Experience Replay for Continual Learning
David Rolnick, Arun Ahuja, Jonathan Schwarz +2
Continual learning is the problem of learning new tasks or knowledge while protecting old knowledge and ideally generalizing from old experience to learn new tasks faster. Neural n…
Learning Latent Dynamics for Planning from Pixels
Danijar Hafner, Timothy Lillicrap, Ian Fischer +4
Planning has been very successful for control tasks with known environment dynamics. To leverage planning in unknown environments, the agent needs to learn the dynamics from intera…
Optimizing Agent Behavior over Long Time Scales by Transporting Value
Chia-Chun Hung, Timothy Lillicrap, Josh Abramson +5
Humans spend a remarkable fraction of waking life engaged in acts of "mental time travel". We dwell on our actions in the past and experience satisfaction or regret. More than mere…
Episodic Curiosity through Reachability
Nikolay Savinov, Anton Raichuk, Raphaël Marinier +4
Rewards are sparse in the real world and most of today's reinforcement learning algorithms struggle with such sparsity. One solution to this problem is to allow the agent to create…
Measuring abstract reasoning in neural networks
David G. T. Barrett, Felix Hill, Adam Santoro +2
Whether neural networks can learn abstract reasoning or whether they merely rely on superficial statistics is a topic of recent debate. Here, we propose a dataset and challenge des…
Noise Contrastive Priors for Functional Uncertainty
Danijar Hafner, Dustin Tran, Timothy Lillicrap +2
Obtaining reliable uncertainty estimates of neural network predictions is a long standing challenge. Bayesian neural networks have been proposed as a solution, but it remains open…
Assessing the Scalability of Biologically-Motivated Deep Learning Algorithms and Architectures
Sergey Bartunov, Adam Santoro, Blake A. Richards +3
The backpropagation of error algorithm (BP) is impossible to implement in a real brain. The recent success of deep networks in machine learning and AI, however, has inspired propos…
Relational Deep Reinforcement Learning
Vinicius Zambaldi, David Raposo, Adam Santoro +13
We introduce an approach for deep reinforcement learning (RL) that improves upon the efficiency, generalization capacity, and interpretability of conventional approaches through st…
Relational recurrent neural networks
Adam Santoro, Ryan Faulkner, David Raposo +7
Memory-based neural networks model temporal data by leveraging an ability to remember information for long periods. It is unclear, however, whether they also have an ability to per…
Distributed Distributional Deterministic Policy Gradients
Gabriel Barth-Maron, Matthew W. Hoffman, David Budden +6
This work adopts the very successful distributional perspective on reinforcement learning and adapts it to the continuous control setting. We combine this within a distributed fram…
The Kanerva Machine: A Generative Distributed Memory
Yan Wu, Greg Wayne, Alex Graves +1
We present an end-to-end trained memory system that quickly adapts to new data and generates samples like them. Inspired by Kanerva's sparse distributed memory, it has a robust dis…
Recall Traces: Backtracking Models for Efficient Reinforcement Learning
Anirudh Goyal, Philemon Brakel, William Fedus +5
In many environments only a tiny subset of all states yield high reward. In these cases, few of the interactions with the environment provide a relevant learning signal. Hence, we…
Unsupervised Predictive Memory in a Goal-Directed Agent
Greg Wayne, Chia-Chun Hung, David Amos +21
Animals execute goal-directed behaviours despite the limited range and scope of their sensors. To cope, they explore environments and store memories maintaining estimates of import…
Fast Parametric Learning with Activation Memorization
Jack W Rae, Chris Dyer, Peter Dayan +1
Neural networks trained with backpropagation often struggle to identify classes that have been observed a small number of times. In applications where most class labels are rare, s…
DeepMind Control Suite
Yuval Tassa, Yotam Doron, Alistair Muldal +9
The DeepMind Control Suite is a set of continuous control tasks with a standardised structure and interpretable rewards, intended to serve as performance benchmarks for reinforceme…