arXiv AI
Aug 7
ProDVI: Programmatic Dynamics Priors for Value Network Initialization
arXiv:2608. 06015v1 Announce Type: cross Abstract: Deep Reinforcement Learning (RL) is notoriously sample inefficient.
ProDVI: Programmatic Dynamics Priors for Value Network Initialization
Deep Reinforcement Learning (RL) is notoriously sample inefficient. One contributing factor is that RL agents are typically initialized from scratch, forcing them to acquire task-relevant knowledge through online interaction.
Related stories
arXiv AI
Jul 16
OPINE-World: Programmatic World Modeling with Ontology-error-Prioritized Interactive Exploration for ARC-AGI-3
arXiv:2607. 01531v2 Announce Type: replace Abstract: Learning how an environment behaves from interaction is central to building agents that adapt to unfamiliar tasks.
arXiv Machine Learning
Jun 17
EnvRL: Learn from Environment Dynamics in Agentic Reinforcement Learning
arXiv:2606. 17680v1 Announce Type: new Abstract: Reinforcement learning (RL) has emerged as a powerful paradigm for training Large Language Models (LLMs) as agents.
arXiv AI
Jul 3
OPINE-World: Programmatic World Modeling with Ontology-error-Prioritized Interactive Exploration
arXiv:2607. 01531v1 Announce Type: new Abstract: Learning how an environment behaves from interaction is central to building agents that adapt to unfamiliar tasks.
Hugging Face Trending Papers
Jul 1
OPINE-World: Programmatic World Modeling with Ontology-error-Prioritized Interactive Exploration
Learning how an environment behaves from interaction is central to building agents that adapt to unfamiliar tasks. World models learned with deep networks are flexible but data-hungry and transfer poorly beyond their training distribution.
arXiv Machine Learning
Jul 16
Pretraining in Actor-Critic Reinforcement Learning for Locomotion
arXiv:2510. 12363v4 Announce Type: replace-cross Abstract: The pretraining-finetuning paradigm has facilitated numerous transformative advancements in artificial intelligence research in recent years.
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 Machine Learning
Jun 25
ACT-JEPA: Novel Joint-Embedding Predictive Architecture for Efficient Policy Representation Learning
arXiv:2501. 14622v5 Announce Type: replace Abstract: Learning efficient representations for decision-making policies is a challenge in imitation learning (IL).
arXiv Computer Vision
6d ago
InternW0-$\Delta$: A World Action Model Bridging Predictive Dynamics and Actions with 20K+ Hours of Open Data
InternW0-Δ is a unified World Action Model that integrates pretrained visual dynamics, scene semantics, 4D geometry, and motion priors within a Mixture-of-Transformers framework to generate robot actions. It leverages a frozen VLM for semantic guidance, a 4D foundation model for geometric priors, and introduces Causal Imprint to learn future-relevant scene changes without future-video rollout. The model is pretrained on a newly curated 20K‑hour heterogeneous corpus of robot and human demonstrations, achieving superior performance on simulation benchmarks and real‑robot platforms.
arXiv AI
Jul 23
In-the-Flow Agentic System Optimization for Effective Planning and Tool Use
arXiv:2510. 05592v2 Announce Type: replace Abstract: Outcome-driven reinforcement learning has advanced reasoning in large language models (LLMs), but prevailing tool-augmented approaches train a single, monolithic policy that interleaves thoughts and tool calls under full context; this scales poorly with long horizons and diverse tools and generalizes weakly to new scenarios.
arXiv AI
2d ago
Your Language Model is Its Own Critic: Reinforcement Learning with Value Estimation from Actor's Internal States
The paper introduces POISE, a reinforcement learning algorithm that uses a model’s internal states as a value estimator to reduce variance in reinforcement learning with verifiable rewards (RLVR). By employing a lightweight probe that reads internal signals during the forward pass, POISE predicts baselines online and uses a cross‑rollout construction to keep gradients unbiased. Experiments on Qwen3‑4B and OLMo3‑7B‑Instruct‑DPO across six domains show POISE outperforms existing RLVR baselines, offering more stable training and a value model that generalizes across tasks and scales with the policy.
arXiv AI
Jun 17
ThinkJEPA: Empowering Latent World Models with Large Vision-Language Reasoning Model
arXiv:2603. 22281v2 Announce Type: replace-cross Abstract: Recent progress in latent world models (e.