10 papers
Sparse Delta Memory: Scaling the State of Linear RNNs through Sparsity
Loïc Cabannes, Pierre-Emmanuel Mazaré, Gergely Szilvasy +6
Linear attention models allow a fixed state size and a fixed amount of compute per token. However, due to their limited state size, linear attention models fall behind in long-cont…
Survival Reinforcement Learning: Toward Scalable Self-Supervised RL
Franki Nguimatsia-Tiofack, Fabian Schramm, Théotime Le Hellard +1
While self-supervised Contrastive Reinforcement Learning (CRL) has shown remarkable depth-scaling capabilities, successfully using networks over 64 layers, scaled CRL still struggl…
SVL: Goal-Conditioned Reinforcement Learning as Survival Learning
Franki Nguimatsia Tiofack, Fabian Schramm, Théotime Le Hellard +1
Standard approaches to goal-conditioned reinforcement learning (GCRL) that rely on temporal-difference learning can be unstable and sample-inefficient due to bootstrapping. While r…
Accelerating trajectory optimization with Sobolev-trained diffusion policies
Théotime Le Hellard, Franki Nguimatsia Tiofack, Quentin Le Lidec +1
Trajectory Optimization (TO) solvers exploit known system dynamics to compute locally optimal trajectories through iterative improvements. A downside is that each new problem insta…
Variance-Reduced Model Predictive Path Integral via Quadratic Model Approximation
Fabian Schramm, Franki Nguimatsia Tiofack, Nicolas Perrin-Gilbert +2
Sampling-based controllers, such as Model Predictive Path Integral (MPPI) methods, offer substantial flexibility but often suffer from high variance and low sample efficiency. To a…
Guided Flow Policy: Learning from High-Value Actions in Offline Reinforcement Learning
Franki Nguimatsia Tiofack, Théotime Le Hellard, Fabian Schramm +2
Offline reinforcement learning often relies on behavior regularization that enforces policies to remain close to the dataset distribution. However, such approaches fail to distingu…
First-order Sobolev Reinforcement Learning
Fabian Schramm, Nicolas Perrin-Gilbert, Justin Carpentier
We propose a refinement of temporal-difference learning that enforces first-order Bellman consistency: the learned value function is trained to match not only the Bellman targets i…
Reference-Free Sampling-Based Model Predictive Control
Fabian Schramm, Pierre Fabre, Nicolas Perrin-Gilbert +1
We present a sampling-based model predictive control (MPC) framework that enables emergent locomotion without relying on handcrafted gait patterns or predefined contact sequences.…
Sampling-Based Global Optimal Control and Estimation via Semidefinite Programming
Antoine Groudiev, Fabian Schramm, Éloïse Berthier +2
Global optimization has gained attraction over the past decades, thanks to the development of both theoretical foundations and efficient numerical routines. Among recent advances,…
Augmented Lagrangian methods for infeasible convex optimization problems and diverging proximal-point algorithms
Roland Andrews, Justin Carpentier, Adrien Taylor
This work investigates the convergence behavior of augmented Lagrangian methods (ALMs) when applied to convex optimization problems that may be infeasible. ALMs are a popular class…