AI that writes the rules: LEARN-Opt designs rewards for robots—no code needed

Kari Jaaskelainen

25 Nov 2025 — 1 min read

TL;DR

Teaching robots with reinforcement learning hinges on the reward function—the 'scorecard' that tells them what to do. Designing good rewards is hard and time-consuming.

LEARN-Opt is a new, fully autonomous approach that lets large language models write, run, and evaluate reward functions from plain-English task descriptions—no environment code or prebuilt metrics needed.

Autonomously derives performance metrics from the task goal.
Matches or outperforms state-of-the-art methods (like EUREKA) with less prior knowledge.
Finds strong solutions even with low-cost LLMs.
Reveals reward design is high-variance—multiple runs help surface the best candidates.

Bottom line: fewer engineering bottlenecks, more generalizable RL control. Paper: https://arxiv.org/abs/2511.19355v1

Paper: https://arxiv.org/abs/2511.19355v1

Register: https://www.AiFeta.com

#AI #ReinforcementLearning #LLM #Robotics #MachineLearning #Automation #Research

Read more

Meet GRACE: a moral governor for safer, more transparent AI

Meet GRACE: a moral governor for safer, more transparent AI

AI agents are getting powerful—so how do we make sure they do the right thing, not just the effective thing? Meet GRACE, a reason-based moral governor that keeps AI behavior aligned with human norms by separating moral reasoning from goal-driven decision-making. * Moral Module: uses deontic logic and explicit reasons

Why some fine-tuned LLMs miss phishing—and how to fix it

Why some fine-tuned LLMs miss phishing—and how to fix it

Not all fine-tuned LLMs spot phishing equally. A new study tests Llama 3.1 8B, Gemma 2 9B, and Mistral on high-stakes phishing detection—and uses SHAP and mechanistic interpretability to reveal why models do (or don’t) generalize. * Architecture × data diversity matters: Gemma 2 9B hits state-of-the-art performance (F1

AI that explains itself—by following the science

AI that explains itself—by following the science

AI that explains itself—by following the science Black-box AI can be powerful, but it often can’t tell us why it made a decision. Concept Bottleneck Models (CBMs) try to fix that by predicting human-understandable concepts first, then the final answer. The catch: standard CBMs ignore domain-specific cause-and-effect and

Meet GenomAgent: A Team of AI Specialists for Smarter Genomics Q&A

Meet GenomAgent: A Team of AI Specialists for Smarter Genomics Q&A

TL;DR: Finding reliable answers in genomics is hard. GenomAgent turns one big AI into a coordinating team of specialists—and beats the current leader by 12% on a key benchmark. Genomic facts live across many databases. Standard chatbots struggle because they can’t flexibly query those sources. GeneGPT added