Multi-agent Reinfocement Learning (AlphaStar)
Key Components V-Trace TD(\(\lambda\)) Architecture [\pi_{\theta}(a_t \vert s_t, z) = \mathbb{P}[a_t \vert s_t, z]] General-purpose Neural Network Components Observation of Units Self-atte...
Zheng Yuan
Lua Notes (World of Warcraft)
Coordinates The bottom right corner is defined as $ (0, 0, 0) $ in a map. Self xyz x = 00ADF4E4 y = 00ADF4E8 z = 00ADF4EC API Action GetActionInfo(slot) - Returns type, id, subtype. Activity...
My Collections - WotLK
Addons Tweaks ElvUI Add Fonts Interface\AddOns\ElvUI\Media Copy file to Interface\AddOns\ElvUI\Media\Fonts\YouyuanHeiti.ttf. Edit SharedMedia.lua. E.Media = { Fonts = {YouyuanHeiti = M....
Reinforcement Learning Notes
Recap of RL Mathematics Basics 🐾 Basics take the Non-incremental Form, Tabular Representation, and are Value-based. Bellman Equation [G_t = R_{t+1} + \gamma G_{t+1}] State Value and Action...
Mathematical Foundations of Reinforcement Learning
Basic Concepts State: The status of the agent with respect to the environment. State Space: The set of all states. \(\mathcal{S} = \{s_i\}_{i=1}^{n}\) Action: All pos...
Principals for Dealing with the Changing World Order
The Big Cycle
Docker Compose Collection
Transmission-TPE services: transmission: image: chisbread/transmission:latest # TR with TPE container_name: transmission-tpe environment: - TZ=Asia/Shanghai - PUID...
Jekyll Post Template
Use space instead of tab for indentation for better compatability. YAML Header --- comments: true title: Jekyll Post Template date: 2024-04-25 12:00:00 image: path: PATH_TO_IMAGE math: true ...
Hopfield Networks
The Hopfield Network Neurons Binary threshold neurons: \(V_i \in \{ 0, 1 \} \text{ or } \{-1, 1 \}\) [V_i = \begin{cases} -1, \text{ Not firing} +1, \text{ Firing at maximum rate} \end{cases...
Nerve Fiber
Types of Nerve Fiber Classification Type Subtype Example Relative Diameter Myelination Sensory&Motor A \(\alpha\)...