ReinforcementLearning
Reinforcement learning (RL) wins in games and simulators—but deploying it on real products is a different story. Gabriel Dulac‑Arnold, Daniel Mankowitz, and Todd Hester outline nine must-solve challenges before RL can safely power real-world systems. * Safety & constraints: avoid harmful actions while learning. * Sample efficiency: learn from limited,
Robotics
What's new PhysWorld lets robots learn skills from AI-generated videos—without collecting any real robot data. How it works * Given a task and one photo of the scene, a video model "imagines" a demonstration. * PhysWorld reconstructs a physics-based world from that video. * An object-centric learner turns
AI
AI finally masters Stratego—on a budget Stratego has long been a worst-case test for AI: you must plan deeply while most pieces are hidden. Big-budget attempts still fell short of top humans. This paper reports a step change: an AI that reaches vastly superhuman Stratego performance—trained for only
AI
Big win for AI in hidden-information games. Stratego has long resisted top-tier AI—even with training runs costing millions. This new study cracks it. Researchers achieved vastly superhuman Stratego play using self-play reinforcement learning plus a smart test-time search designed for imperfect information. The surprise: it worked with only a
Robotics
What if robots could learn new tasks just by watching AI-generated videos - and still obey physics? PhysWorld is a new framework that turns text-and-image prompts into physically executable robot skills. * It first generates a task-conditioned video from a single scene image and a command. * Then it reconstructs the scene&
AI
AI that sees, thinks—and uses tools Meet DeepEyesV2, a multimodal “agentic” model that doesn’t just read text and look at images—it can call external tools like code runners and web search, then weave the results into its reasoning. Key ideas: * Two-stage training: a cold-start phase teaches basic
AI
Struggling to compare or improve your automations? Opus offers a simple, quantitative way to score and optimize any Workflow—so you can pick what works, fix what doesn’t, and waste fewer resources. What’s inside * Opus Workflow Reward: a probabilistic score that blends likelihood of success, resource usage, and
AI
Getting AI to reflect human preferences usually means showing it lots of examples—which is slow and costly. This paper proposes a smarter path: combine the scale of RLHF (used to tune large language models) with the efficiency of Bayesian preference optimization (PBO), which actively chooses the most informative questions
AI
LLMs are starting to act as “agents,” making choices in dynamic settings—but they often struggle with exploration vs. exploitation and rack up high regret (missed reward vs. the best strategy in hindsight). A new approach, Iterative Regret-Minimization Fine-Tuning (Iterative RMFT), trains models to decide better by learning from their
ImitationLearning
What if AI could learn skills the way people do - by watching and copying? This new survey maps the fast-moving world of imitation learning (IL) in the deep learning era. * Data: from full expert trajectories to partial or unlabeled sequences. * New methods tackle big pain points: generalization, covariate shift,