arXiv Machine Learning
ZipDrift: Generating Multimodal Short-Horizon MPC Costs with One-Step Drifting Models
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv AI
Jul 16
Adapting Generalist Vehicle Models for High-Speed MPC Across Terrains
arXiv:2607. 13319v1 Announce Type: cross Abstract: High-speed off-road autonomy requires precise closed-loop control for a target vehicle while remaining robust across changing terrains.
arXiv Machine Learning
Jul 14
A Control Theory of Predictability in Latent World Models
arXiv:2607. 10362v1 Announce Type: new Abstract: Latent world models are trained to predict future states in a learned representation and are then deployed inside a planner that selects actions by simulating them forward.
arXiv AI
Oct 21
Adaptive Multi-Token Prediction: How far should we go?
arXiv:2610.28619v1 Announce Type: new Abstract: Multi-token prediction (MTP) can accelerate language-model decoding by drafting several tokens and verifying them in a single target-model pass. Howeve...
arXiv AI
Aug 14
The Objective Is the Bottleneck: Latent World Models Encode What Their Planners Cannot Use
arXiv:2608. 12959v1 Announce Type: cross Abstract: Latent world models are judged by how well they predict, so when planning fails at long horizons the natural reading is that the predictor degrades.
arXiv AI
Sep 25
AD-WM: Action-Discriminative World Models for Counterfactual Model Predictive Control
AD-WM is a new action‑discriminative joint‑embedding world model designed for counterfactual model predictive control. It augments residual latent dynamics with action‑recovery regularization based on inverse dynamics and conditional mutual information, while discarding auxiliary heads at test time so that MPC remains unchanged. Experiments on OGBench‑Cube and other simulation environments show substantial gains in hard‑start success and mean success, and zero‑shot transfer to a Franka robot improves pick‑and‑place success from 42.2% to 71.1%.
arXiv Machine Learning
Aug 28
Shared Actors Need Not Share Critics: Effects of Value Mismatch in Parallel Reinforcement Learning
The paper investigates the problem of sharing a single critic across multiple parallel environments in reinforcement learning. It shows that when environments assign different expected returns to the same state, a shared critic must reconcile conflicting value targets, which can distort advantage estimates and misguide policy updates. The authors propose a simple fix—providing the critic with the environment index—demonstrating through bandit models and experiments on CartPole, MuJoCo, BipedalWalker, and 16 Procgen games that this conditional critic stabilizes learning and boosts returns, achieving a 40.8% improvement in aggregate normalized return on unseen levels.