Natural Language Actor-Critic: Scalable Off-Policy Learning in Language Space

arXiv:2512.04601 · cs.LG, cs.CL · Submitted 2025-12-04 · Read on arXiv

cs.LG, cs.CL

Submitted: 2025-12-04

Updated: 2026-10-30

Terminology

• Actor — 3× in this paper · explained in 3 episodes
• Natural Language Actor-Critic — 2× in this paper
• Large Language Model (LLM) — 1× in this paper · explained in 3 episodes
• Reward Function — 1× in this paper · explained in 5 episodes
• Sample Complexity — 1× in this paper · explained in 20 episodes

Related papers

• Power Distribution Bridges Sampling, Self-Reward RL, and Self-Distillation
• Train Separately, Merge Together: Modular Post-Training with Mixture-of-Experts
• Democratizing Tool Learning with Environments Fully Simulated by a Free 8B Language Model
• D-STEER: Two-Way Control of DPO-Induced Safety Behavior in Activation Space
• Optimal hypersurface decision trees
• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation