#policy-gradient

The latest AI and developer news about #policy-gradient, with the original source and a short summary.

The Gradient Is a Covariance: Why Post-Training Updates Are Sparse

The expected gradient is a covariance and the Fisher is a variance, capping updates at |G| ≤ std(A) · √F.

·2026.10.15 09:00

Deriving Policy Gradients for LLMs: From REINFORCE to GRPO and Handling Inference Mismatch

This article derives policy gradient methods for LLMs, explaining how REINFORCE evolves into GRPO through baseline variance reduction and addressing the gradient bias caused by inference engine mismatches.

·2026.09.27 16:00

PPM Framework Addresses Sparse Reward Inefficiency in Long-Horizon LLM Reasoning

PPM is a framework that addresses the inefficiency of sparse rewards in long-horizon LLM reasoning and guarantees optimal policies.

·2026.09.09 09:00

Building AI Agents from First Principles

Without relying on any framework, this piece explains the core principles of training reinforcement-learning-based agents—from defining the environment to designing the reward function—using a diagram agent example.

·2026.05.20 09:00

Entropy-Preserving Reinforcement Learning

Controlling the entropy-reducing tendency of policy gradient training preserves exploration diversity.

·1·2026.03.30 09:00