A series of macro and micro optimizations to make Puffer RL training faster and scale better.
Scaling RL: GPU multithreaded batching with Puffer
Demo 2D Pixel Platformer To Explore Self-Play & Reinforcement Learning
(requires: desktop browser + keyboard / game controller)Hello! I am a software engineer. I am building a mindfulness game/app.
I am also exploring and exploiting reinforcement learning for fun and serious learning.
You can read my blog below where I write about my learnings in reinforcement learning.Latest Blog Posts
Pixel Platformer Demo: Explore RL and Self-Play
Using a toy but playable pixel platformer to create agents that can play along-side you.
Deconstructing a 1-bit LSTM
(Part 2/2) Understanding the internals of an LSTM by (de)constructing an 1-bit LSTM.
Draw with an LSTM
(Part 1/2) A creative coding experiment to explore LSTMs with your touch
