Skip to content

Embedded reinforcement learning project done as Yale senior project, incorporating the Bush-Mosteller online learning algorithm

Notifications You must be signed in to change notification settings

itsjameszhao/Embedded-Reinforcement-Learning

Repository files navigation

Matching Pennies CSEC 491 Project

This project investigates the feasibility of deploying online learning algorithms on low-power, low-cost embedded systems. We explore this problem by implementing a mind-reading algorithm inspired by Shannon's Mind Reading Paper and SEER (a sequence extracting robot) on a MicroBit embedded system to play the Matching Pennies game. We compare the performance of heuristic-based and reinforcement learning strategies under various memory and processor constraints. Additionally, we conduct a user study to validate our approach against human opponents. Our results demonstrate that online learning algorithms can be effectively deployed on embedded systems, providing new avenues for expansion, such as machine learning functionality through pruning and quantization, risk-aversion quantification, and federated learning approaches.

Demo

This is a demo of the embedded reinforcement learning algorithm beating the user at a game of matching pennies over 20 trials, first to 10.

View Demo Video

Initial Proposal

View Initial Proposal

Senior Project Final Report

View Report

Code Zip

Download .zip

More code and files can be found on GitHub.

About

Embedded reinforcement learning project done as Yale senior project, incorporating the Bush-Mosteller online learning algorithm

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published