arXiv Machine Learning
Teaching Agents the "Principle", Not the "Reward"
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv Machine Learning
Jul 22
HERAKLES: Hierarchical Skill Compilation for Open-ended LLM Agents
arXiv:2508. 14751v2 Announce Type: replace Abstract: We study goal-conditioned reinforcement learning in partially observable environments with sparse rewards and large, structured goal spaces.
arXiv AI
Oct 26
Effectiveness of Curriculum Learning Depends on Reward Sparsity and Competing Optima
The paper investigates how curriculum learning affects reinforcement learning in a minimal policy learning model. It shows that when rewards are dense, curricula offer only marginal benefits, but when rewards are sparse, curricula become essential for learning to occur. The study also highlights that competing objectives—minimizing effort versus maximizing reward—create distinct optima that curricula can help navigate by reducing reward sparsity and reshaping the reward landscape.
arXiv Machine Learning
Jun 8
Self-evolving LLM agents with in-distribution Optimization
arXiv:2606. 07367v1 Announce Type: new Abstract: Large Language Models (LLMs) have recently emerged as powerful controllers for interactive agents in complex environments, yet training them to perform reliable long-horizon decision making remains a fundamental challenge.
arXiv Machine Learning
Aug 11
Multi-Agent Reinforcement Learning via Agent-Specific Preference
arXiv:2608. 08604v1 Announce Type: new Abstract: Multi-agent reinforcement learning (MARL) is a powerful framework for solving complex collaborative tasks, but it relies heavily on well-defined global reward functions.
arXiv AI
Jul 7
ARLArena: A Unified Framework for Stable Agentic Reinforcement Learning
arXiv:2602. 21534v3 Announce Type: replace Abstract: Agentic reinforcement learning (ARL) has rapidly gained attention as a promising paradigm for training agents to solve complex, multi-step interactive tasks.
arXiv AI
Sep 2
Selective Agent Guidance via Entropy: Learning Autonomous Policies from Imperfect VLM Teachers
The paper introduces SAGE, a framework that selectively queries a Vision‑Language Model (VLM) teacher only when the learner is uncertain, using the teacher’s suggestions to guide training and distill them into a lightweight reinforcement learning policy. SAGE weights teacher actions by environment‑derived advantages, allowing the policy to improve beyond the imperfect VLM. Experiments on sparse‑reward visual reasoning and navigation tasks show that the learned policies can act without VLM guidance at evaluation, reduce VLM usage during training, and sometimes outperform the teacher itself.