143 citations · 308 across the 55 of their papers we have counts for
7 papers · 1 filter
Maximum entropy GFlowNets with soft Q-learning
Sobhan Mohammadpour, Emmanuel Bengio, Emma Frejinger +1
Generative Flow Networks (GFNs) have emerged as a powerful tool for sampling discrete objects from unnormalized distributions, offering a scalable alternative to Markov Chain Monte…
Course Correcting Koopman Representations
Mahan Fathi, Clement Gehring, Jonathan Pilault +3
Koopman representations aim to learn features of nonlinear dynamical systems (NLDS) which lead to linear dynamics in the latent space. Theoretically, such features can be used to s…
Motif: Intrinsic Motivation from Artificial Intelligence Feedback
Martin Klissarov, Pierluca D'Oro, Shagun Sodhani +5
Exploring rich environments and evaluating one's actions without prior knowledge is immensely challenging. In this paper, we propose Motif, a general method to interface such prior…
Policy Optimization in a Noisy Neighborhood: On Return Landscapes in Continuous Control
Nate Rahn, Pierluca D'Oro, Harley Wiltzer +2
Deep reinforcement learning agents for continuous control are known to exhibit significant instability in their performance over time. In this work, we provide a fresh perspective…
When Do Transformers Shine in RL? Decoupling Memory from Credit Assignment
Tianwei Ni, Michel Ma, Benjamin Eysenbach +1
Reinforcement learning (RL) algorithms face two distinct challenges: learning effective representations of past and present observations, and determining how actions influence futu…
Goal-conditioned GFlowNets for Controllable Multi-Objective Molecular Design
Julien Roy, Pierre-Luc Bacon, Christopher Pal +1
In recent years, in-silico molecular design has received much attention from the machine learning community. When designing a new compound for pharmaceutical applications, there ar…
Block-State Transformers
Mahan Fathi, Jonathan Pilault, Orhan Firat +3
State space models (SSMs) have shown impressive results on tasks that require modeling long-range dependencies and efficiently scale to long sequences owing to their subquadratic r…