arXiv Machine Learning
Imagining Goals with Geometric Horizon Models for Policy Generalization
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 14
Training on Irrelevant States Implies Data Augmentation: Generalization in Contextual MDPs
arXiv:2410. 03565v4 Announce Type: replace-cross Abstract: In the zero-shot policy transfer (ZSPT) setting for contextual Markov decision processes (CMDP), agents train on a fixed, finite set of contexts and must generalize to new ones.
arXiv AI
Jun 17
EvolveNav: Proactive Preflection and Self-Evolving Memory for Zero-Shot Object Goal Navigation
arXiv:2606. 18235v1 Announce Type: new Abstract: Zero-Shot Object-Goal Navigation (ZS-OGN) requires embodied agents to explore and locate target objects without any prior training.
arXiv AI
Jun 2
From Demonstrations to Rewards: Test-Time Prompt Optimization for VLM Reward Models
arXiv:2606. 00083v1 Announce Type: cross Abstract: Reinforcement learning relies on accurate reward functions, which are often hand-crafted or even unavailable in real-world applications, such as robotics.
arXiv Computer Vision
Aug 27
Zero-WAM: In-Context World-Action Modeling from Human Videos for Open-Ended Task Generalization
Zero-WAM introduces a causal video-action model that enables robots to perform unseen manipulation tasks by following in-context human video guidance. The authors create HumanGen, a dataset of 74.2K human-robot ICL pairs across 8.6K tasks, and propose an in-context future chunk prediction objective to prevent shortcut learning. In simulation, Zero-WAM attains a 47.0% success rate on seven unseen tasks, outperforming the best video-action baseline by 29.5 percentage points, and demonstrates real‑world generalization to complex, long‑horizon, and fine‑grained tasks.
arXiv Computer Vision
Oct 8
Video Prediction Policy 2: Predict Better, Act Better
Video Prediction Policy 2 (VPP2) is a new world action model that improves zero‑shot generalization for both video prediction and action generation. It achieves this by pretraining a large, diverse manipulation video dataset with event‑level supervision, then distilling the model into a single‑step visual planner and adding a mixture‑of‑transformers action module. Experiments show VPP2 outperforms leading baselines on open‑ended video prediction, real‑world zero‑shot manipulation, and several challenging benchmarks.
arXiv AI
Jun 15
Unsupervised Learning of Efficient Exploration: Pre-training Adaptive Policies via Self-Imposed Goals
arXiv:2601. 19810v2 Announce Type: replace-cross Abstract: Unsupervised pre-training can equip reinforcement learning agents with prior knowledge and accelerate learning in downstream tasks.