Tech 66
- Anthropic's J-Space: A Global Workspace Inside Language Models
- The Bitter Lesson and Reward is Enough: Sutton's Two Principles of Intelligence
- From Noise to Data: An Introduction to Diffusion Models
- Policy-Conditioned Policies for Multi-Agent Task Solving
- Talk, Judge, Cooperate: Gossip-Driven Indirect Reciprocity in Self-Interested LLM Agents
- Verbalized Bayesian Persuasion
- Dynamic Programming
- A* Search Algorithm
- Computational Complexity: P, NP, PPAD and Game Theory
- Auctions and Mechanism Design
- MS-Swift GRPO Pipeline Walkthrough
- Mean-Field Game
- LLM x RL
- LLM Architecture Speedrun
- Minimal LLM Agent
- PSRO: Policy-Space Response Oracles
- Obsidian-Based Workspace
- Cheap Talk
- Llama Memo
- GPT
- Transformer
- Bargaining
- Extensive-Form Games and Subgame Perfect Equilibrium
- Mathematica Memos
- Building My Own PC
- TRPO Details
- Fairness Versus Reason in the Ultimatum Game
- Evolutionary Game Theory
- Code Visualization
- LyPythonToolbox
- Github Memo
- Python Project Template
- 多智能体强化学习中的信息设计
- Information Design in Multi-Agent Reinforcement Learning
- My Website
- MacOS Workspace
- PyTorch Toolbox
- Python Toolbox
- Stable Baseline 3
- Overcooked: A MARL Task
- Tools of Visual Studio Code
- HyperNetworks
- Decision Transformers
- Contraction Mapping Theorem
- A Note on Stochastic Processes
- Zero-Determinant Strategy
- Classic Games
- Information Design in 10 Minutes
- A Memo on Game Theory
- Fictitious Self-Play and Zero-Shot Coordination
- Policy Gradient Details
- RNNs
- MARL Basics
- Computation Graph Visualization
- Dynamic Epistemic Logic
- Theory of Mind and Markov Models
- Information Design
- RL Toolbox
- Misc Code Toolbox
- Math Toolbox
- Swinging Search and Crawling Control
- RHex-T3: A Mobile Robot, with Hybrid Leg Design
- MARL Seminar | Simultaneously Learning and Advising in MARL
- MARL Seminar | MADDPG
- MARL Seminar | CommNet
- MARL Seminar | Public Sanctions