research
∙
01/13/2022
Pushing the limits of self-supervised ResNets: Can we outperform supervised learning without labels on ImageNet?
Despite recent progress made by self-supervised methods in representatio...
share
research
∙
11/18/2020
Counterfactual Credit Assignment in Model-Free Reinforcement Learning
Credit assignment in reinforcement learning is the problem of measuring ...
research
∙
11/08/2020
On the role of planning in model-based deep reinforcement learning
Model-based planning is often thought to be necessary for deep, careful ...
research
∙
10/15/2020
Representation Learning via Invariant Causal Mechanisms
Self-supervised learning has emerged as a strategy to reduce the relianc...
research
∙
10/03/2020
Beyond Tabula-Rasa: a Modular Reinforcement Learning Approach for Physically Embedded 3D Sokoban
Intelligent robots need to achieve abstract objectives using concrete, s...
research
∙
09/11/2020
Physically Embedded Planning Problems: New Challenges for Reinforcement Learning
Recent work in deep reinforcement learning (RL) has produced algorithms ...
research
∙
06/11/2020
Pointer Graph Networks
Graph neural networks (GNNs) are typically applied to static graphs that...
research
∙
04/23/2020
Divide-and-Conquer Monte Carlo Tree Search For Goal-Directed Planning
Standard planners for sequential decision making (including Monte Carlo ...
research
∙
02/19/2020
Value-driven Hindsight Modelling
Value estimation is a critical component of the reinforcement learning (...
research
∙
02/07/2020
Causally Correct Partial Models for Reinforcement Learning
In reinforcement learning, we can learn a model of future observations a...
research
∙
12/05/2019
Combining Q-Learning and Search with Amortized Value Estimates
We introduce "Search with Amortized Value Estimates" (SAVE), an approach...
research
∙
10/15/2019
Approximate Inference in Discrete Distributions with Monte Carlo Tree Search and Value Functions
A plethora of problems in AI, engineering and the sciences are naturally...
research
∙
01/07/2019
Credit Assignment Techniques in Stochastic Computation Graphs
Stochastic computation graphs (SCGs) provide a formalism to represent st...
research
∙
11/15/2018
Woulda, Coulda, Shoulda: Counterfactually-Guided Policy Search
Learning policies on data synthesized by models can in principle quench ...
research
∙
02/08/2018
Learning and Querying Fast Generative Models for Reinforcement Learning
A key challenge in model-based reinforcement learning (RL) is to synthes...
research
∙
11/06/2017
Fast amortized inference of neural activity from calcium imaging data with variational autoencoders
Calcium imaging permits optical measurement of neural activity. Since in...
research
∙
07/19/2017
Imagination-Augmented Agents for Deep Reinforcement Learning
We introduce Imagination-Augmented Agents (I2As), a novel architecture f...
research
∙
07/19/2017
Learning model-based planning from scratch
Conventional wisdom holds that model-based planning is a powerful approa...
research
∙
11/23/2015
Black box variational inference for state space models
Latent variable time-series models are among the most heavily used tools...
research
∙
10/24/2014