Tagged articles

entropy regularization

2 articles · Page 1 of 1

Sep 17, 2026 · Artificial Intelligence

LLM Post-Training Paradigm Shift: 5 New Paths Replacing Monolithic RL

This article analyzes five fundamental shifts in LLM post-training over the past six months: moving from monolithic RL to expert distillation (MOPD), online distillation as a 10x cheaper RL alternative, refined RLVR techniques addressing entropy collapse and exploration, SFT-RL distribution alignment, and data quality as an irrecoverable hard constraint.

LLM Post-TrainingMiMo-V2-FlashRLVR

0 likes · 9 min read

LLM Post-Training Paradigm Shift: 5 New Paths Replacing Monolithic RL

Code DAO

Nov 28, 2021 · Artificial Intelligence

Adapting Soft Actor‑Critic for Discrete Action Spaces in Deep Reinforcement Learning

This article explains how to modify the Soft Actor‑Critic (SAC) algorithm—originally designed for continuous actions—to work with discrete action environments, presents the required changes to the actor and critic loss functions, provides a full PyTorch implementation, and evaluates the method on the CartPole‑v1 benchmark.

CartPoleDiscrete ActionsOpenAI Gym

0 likes · 20 min read

Adapting Soft Actor‑Critic for Discrete Action Spaces in Deep Reinforcement Learning