arXiv AI
Learning Local Constraints for Reinforcement-Learned Content Generators
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
3d ago
Conditional Generation of Creative Chess Puzzles with Diffusion Models
The paper presents a method for generating creative chess puzzles using masked diffusion models that can be conditioned on tactical themes and partial board positions. It introduces an auxiliary best‑move prediction task that boosts solution uniqueness by 11.6% and theme‑conditioning accuracy by 2.5%. A reinforcement learning framework further increases the yield of unique, theme‑matching puzzles by 89.1%, and the authors release open‑weights models for the community.
arXiv AI
Jul 21
PPO-HSC: An Exploratory Reinforcement Learning Framework Based on Wide-Area Policy Coverage Optimization
arXiv:2607. 16206v1 Announce Type: new Abstract: This paper introduces PPO-HSC (Proximal Policy Optimization with High-order Sampling Coverage), an exploratory reinforcement learning framework designed to address the "Invisible Shackles" of mode collapse in Large Language Model (LLM) fine-tuning.
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
Jul 3
Evolutionary Wave Function Collapse
arXiv:2607. 02082v1 Announce Type: cross Abstract: Wave Function Collapse (WFC) is a widely used procedural content generation method that learns local adjacency constraints from example inputs to generate larger outputs.
arXiv AI
Sep 23
Which Constraints Are Missing? Ask the Verifier: Graded Rewards for Constraint-Following Music Generation
arXiv:2609.23665v1 Announce Type: cross Abstract: Constraint-following music generation asks a score to satisfy several user-specified properties at once, each checkable programmatically (key, meter,...
arXiv AI
Jul 2
Right in the Right Way: LM Training with Verifiable Rewards and Human Demonstrations
arXiv:2607. 01181v1 Announce Type: cross Abstract: RL with verifiable rewards (RLVR) has emerged as a powerful paradigm for training LMs on tasks with well-defined success metrics, such as code generation and mathematical reasoning.