Search Results for author:
Found 20 papers, 10 papers with code
Curiosity in hindsight
In this work, we study a natural solution derived from structural causal models of the world: Our key idea is to learn representations of the future that capture precisely the unpredictable aspects of each outcome -- not any more, not any less -- which we use as additional input for predictions, such that intrinsic rewards do vanish in the limit.
Self-conditioned Embedding Diffusion for Text Generation
Can continuous diffusion models bring the same performance breakthrough on natural language they did for image generation?
Emergent Communication: Generalization and Overfitting in Lewis Games
Lewis signaling games are a class of simple communication games for simulating the emergence of language.
BYOL-Explore: Exploration by Bootstrapped Prediction
We present BYOL-Explore, a conceptually simple yet general approach for curiosity-driven exploration in visually-complex environments.
Shaking the foundations: delusions in sequence models for interaction and control
The recent phenomenal success of language models has reinvigorated machine learning research, and large sequence models such as transformers are being applied to a variety of domains.
Emergent Communication at Scale
Emergent communication aims for a better understanding of human language evolution and building more efficient representations.
Density-Based Bonuses on Learned Representations for Reward-Free Exploration in Deep Reinforcement Learning
In this paper, we study the problem of representation learning and exploration in reinforcement learning.
Broaden Your Views for Self-Supervised Video Learning
Most successful self-supervised learning methods are trained to align the representations of two independent views from the data.
Ranked #1 on
Self-Supervised Audio Classification
on ESC-50
Bootstrapped Representation Learning on Graphs
Current state-of-the-art self-supervised learning methods for graph neural networks are based on contrastive learning.
Large-Scale Representation Learning on Graphs via Bootstrapping
To address these challenges, we introduce Bootstrapped Graph Latents (BGRL) - a graph representation learning method that learns by predicting alternative augmentations of the input.
Learning Successor States and Goal-Dependent Values: A Mathematical Viewpoint
In reinforcement learning, temporal difference-based algorithms can be sample-inefficient: for instance, with sparse rewards, no learning occurs until a reward is observed.
Bootstrap Your Own Latent - A New Approach to Self-Supervised Learning
From an augmented view of an image, we train the online network to predict the target network representation of the same image under a different augmented view.
BYOL works even without batch statistics
Bootstrap Your Own Latent (BYOL) is a self-supervised learning approach for image representation.
Bootstrap your own latent: A new approach to self-supervised Learning
From an augmented view of an image, we train the online network to predict the target network representation of the same image under a different augmented view.
Ranked #2 on
Self-Supervised Person Re-Identification
on SYSU-30k
Representation Learning
Self-Supervised Image Classification
+3
Making Deep Q-learning methods robust to time discretization
Despite remarkable successes, Deep Reinforcement Learning (DRL) is not robust to hyperparameterization, implementation details, or small environment changes (Henderson et al. 2017, Zhang et al. 2018).
Mixed batches and symmetric discriminators for GAN training
We propose to feed the discriminator with mixed batches of true and fake samples, and train it to predict the ratio of true samples in the batch.
Can recurrent neural networks warp time?
Successful recurrent models such as long short-term memories (LSTMs) and gated recurrent units (GRUs) use ad hoc gating mechanisms.
Unbiasing Truncated Backpropagation Through Time
Truncated BPTT keeps the computational benefits of Backpropagation Through Time (BPTT) while relieving the need for a complete backtrack through the whole data sequence at every step.
Unbiased Online Recurrent Optimization
The novel Unbiased Online Recurrent Optimization (UORO) algorithm allows for online learning of general recurrent computational graphs such as recurrent network models.
Training recurrent networks online without backtracking
The evolution of this search direction is partly stochastic and is constructed in such a way to provide, at every time, an unbiased random estimate of the gradient of the loss function with respect to the parameters.
