Corentin Tallec
Phd Student (LRI Saclay)
Consider the exploration in sparse-reward or reward-free environments, s...
Can continuous diffusion models bring the same performance breakthrough ...
Lewis signaling games are a class of simple communication games for
simu...
We present BYOL-Explore, a conceptually simple yet general approach for
...
The recent phenomenal success of language models has reinvigorated machi...
Most successful self-supervised learning methods are trained to align th...
Current state-of-the-art self-supervised learning methods for graph neur...
In reinforcement learning, temporal difference-based algorithms can be
s...
Bootstrap Your Own Latent (BYOL) is a self-supervised learning approach ...
We introduce Bootstrap Your Own Latent (BYOL), a new approach to
self-su...
Despite remarkable successes, Deep Reinforcement Learning (DRL) is not r...
Generative adversarial networks (GANs) are pow- erful generative models ...
Successful recurrent models such as long short-term memories (LSTMs) and...
Truncated Backpropagation Through Time (truncated BPTT) is a widespread
...
The novel Unbiased Online Recurrent Optimization (UORO) algorithm allows...
We introduce the "NoBackTrack" algorithm to train the parameters of dyna...