Reinforcement Learning - Naifan Li's Blog

Reinforcement Learning - Naifan Li's Bloghttps://blog.omagiclee.com/categories/reinforcement-learning/Reinforcement Learning - Naifan Li's BlogHugo -- gohugo.iozh-CNMon, 29 May 2023 20:20:00 +0800Direct Preference Optimization (DPO): Your Language Model is Secretly a Reward Modelhttps://blog.omagiclee.com/posts/reinforcement-learning/dpo/Mon, 29 May 2023 20:20:00 +0800https://blog.omagiclee.com/posts/reinforcement-learning/dpo/ arXiv 2305.18290

TL;DR

Motivations & Innovations

Approach

Model

Training Recipe

Data Recipe

Experiments

]]>PPO: Proximal Policy Optimization Algorithmshttps://blog.omagiclee.com/posts/reinforcement-learning/ppo/Thu, 20 Jul 2017 20:20:04 +0800https://blog.omagiclee.com/posts/reinforcement-learning/ppo/OpenAI arXiv 1707.06347

TL;DR

Motivations & Innovations

Approach

Model

Training Recipe

Data Recipe

Experiments

]]>