Writers/Fellow
thanhpn
Former Blockchain
Written at Dwarves
Latest- 3 Jul 2024Proximal policy optimization
Proximal policy optimization (PPO) is an algorithm that aims to improve the stability of training by avoiding overly large policy updates. It is a popular and effective method used for training [ reinforcement learning](#wikilink:Reinforcement%20Learning) models in complex environments. To achieve this, PPO uses a ratio that indicates the difference between the current policy and the old policy and clips this ratio within a specific range, ensuring that the policy updates are not too large and the training process is more stable...
- 23 Jun 2023Reward model
A Reward model is a critical component in Reinforcement Learning for Large Language Models (LLMs), designed to evaluate and score the quality of generated responses. It plays a key role in aligning LLMs with human values and improving their output through iterative refinement.
- 22 Jun 2023Q learning
An introduction to Q-learning, a model-free reinforcement learning algorithm used to learn optimal policies in Markov Decision Processes.
All notes
13- 3 Jul 2024Proximal policy optimizationResearch notesApplied LLMs
- 23 Jun 2023Reward modelResearch notesApplied LLMs
- 22 Jun 2023Q learningResearch notesApplied LLMs
- 5 Jun 2023Introduction to reinforcement learning and its application with LLMsResearch notesApplied LLMs
- 18 May 2023Choosing a vector database for LLM applicationsResearch notesApplied LLMs
- 26 Dec 2022Starknet architecture, components and transaction lifecycleResearch notesDigital assets
- 6 Sep 2022Zero-knowledge proofsResearch notesDigital assets
- 10 Aug 2022Multisign walletResearch notesDigital assets
- 21 Jun 2022Blockchain bridgeResearch notesDigital assets
- 16 Jun 2022BlocksResearch notesDigital assets
- 16 Jun 2022Distributed systemsResearch notesDigital assets
- 16 Jun 2022PoSResearch notesDigital assets
- 16 Jun 2022Smart contractResearch notesDigital assets