Search Results for author:
Found 27 papers, 7 papers with code
Pushing the limits of self-supervised ResNets: Can we outperform supervised learning without labels on ImageNet?
Most notably, ReLICv2 is the first unsupervised representation learning method to consistently outperform the supervised baseline in a like-for-like comparison over a range of ResNet architectures.
Ranked #14 on
Semantic Segmentation
on PASCAL VOC 2012 val
Counterfactual Credit Assignment in Model-Free Reinforcement Learning
Credit assignment in reinforcement learning is the problem of measuring an action's influence on future rewards.
On the role of planning in model-based deep reinforcement learning
These results indicate where and how to utilize planning in reinforcement learning settings, and highlight a number of open questions for future MBRL research.
Model-based Reinforcement Learning
reinforcement-learning
+1
Representation Learning via Invariant Causal Mechanisms
Self-supervised learning has emerged as a strategy to reduce the reliance on costly supervised signal by pretraining representations only using unlabeled data.
Ranked #77 on
Self-Supervised Image Classification
on ImageNet
Beyond Tabula-Rasa: a Modular Reinforcement Learning Approach for Physically Embedded 3D Sokoban
We explore whether integrated tasks like Mujoban can be solved by composing RL modules together in a sense-plan-act hierarchy, where modules have well-defined roles similarly to classic robot architectures.
Physically Embedded Planning Problems: New Challenges for Reinforcement Learning
To encourage progress towards this goal we introduce a set of physically embedded planning problems and make them publicly available.
Pointer Graph Networks
This static input structure is often informed purely by insight of the machine learning practitioner, and might not be optimal for the actual task the GNN is solving.
Divide-and-Conquer Monte Carlo Tree Search For Goal-Directed Planning
are constrained by an implicit sequential planning assumption: The order in which a plan is constructed is the same in which it is executed.
Value-driven Hindsight Modelling
Value estimation is a critical component of the reinforcement learning (RL) paradigm.
Causally Correct Partial Models for Reinforcement Learning
In reinforcement learning, we can learn a model of future observations and rewards, and use it to plan the agent's next actions.
Combining Q-Learning and Search with Amortized Value Estimates
In SAVE, a learned prior over state-action values is used to guide MCTS, which estimates an improved set of state-action values.
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 formalized as inference in discrete probabilistic models.
Credit Assignment Techniques in Stochastic Computation Graphs
Stochastic computation graphs (SCGs) provide a formalism to represent structured optimization problems arising in artificial intelligence, including supervised, unsupervised, and reinforcement learning.
Woulda, Coulda, Shoulda: Counterfactually-Guided Policy Search
In contrast to off-policy algorithms based on Importance Sampling which re-weight data, CF-GPS leverages a model to explicitly consider alternative outcomes, allowing the algorithm to make better use of experience data.
Temporal Difference Variational Auto-Encoder
To act and plan in complex environments, we posit that agents should have a mental simulator of the world with three characteristics: (a) it should build an abstract state representing the condition of the world; (b) it should form a belief which represents uncertainty on the world; (c) it should go beyond simple step-by-step simulation, and exhibit temporal abstraction.
Learning and Querying Fast Generative Models for Reinforcement Learning
A key challenge in model-based reinforcement learning (RL) is to synthesize computationally efficient and accurate environment models.
Learning Dynamic State Abstractions for Model-Based Reinforcement Learning
A key challenge in model-based reinforcement learning (RL) is to synthesize computationally efficient and accurate environment models.
Fast amortized inference of neural activity from calcium imaging data with variational autoencoders
Calcium imaging permits optical measurement of neural activity.
Learning model-based planning from scratch
Here we introduce the "Imagination-based Planner", the first model-based, sequential decision-making agent that can learn to construct, evaluate, and execute plans.
Imagination-Augmented Agents for Deep Reinforcement Learning
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
Black box variational inference for state space models
These models have the advantage of learning latent structure both from noisy observations and from the temporal ordering in the data, where it is assumed that meaningful correlation structure exists across time.
Clustered factor analysis of multineuronal spike data
High-dimensional, simultaneous recordings of neural spiking activity are often explored, analyzed and visualized with the help of latent variable or factor models.
Bayesian Manifold Learning: The Locally Linear Latent Variable Model (LL-LVM)
We introduce the Locally Linear Latent Variable Model (LL-LVM), a probabilistic model for non-linear manifold discovery that describes a joint distribution over observations, their manifold coordinates and locally linear maps conditioned on a set of neighbourhood relationships.
Inferring neural population dynamics from multiple partial recordings of the same neural circuit
Simultaneous recordings of the activity of large neural populations are extremely valuable as they can be used to infer the dynamics and interactions of neurons in a local circuit, shedding light on the computations performed.
Spectral learning of linear dynamics from generalised-linear observations with application to neural population data
Here, we show how spectral learning methods for linear systems with Gaussian observations (usually called subspace identification in this context) can be extended to estimate the parameters of dynamical system models observed through non-Gaussian noise models.
Empirical models of spiking in neural populations
Neurons in the neocortex code and compute as part of a locally interconnected population.
Simplified Rules and Theoretical Analysis for Information Bottleneck Optimization and PCA with Spiking Neurons
We show that under suitable assumptions (primarily linearization) a simple and perspicuous online learning rule for Information Bottleneck optimization with spiking neurons can be derived.
