Offline Reinforcement Learning for autonomous driving
EECS 545 Winter 2024 final project report and code. Using INTERACTION dataset to learn human driving behaviour using reinforcement learning
You May Also Enjoy
The Math Behind In-Context Learning Permalink
less than 1 minute read
From attention to gradient descent: unraveling how transformers learn from examples
Linearizing Attention Permalink
less than 1 minute read
Breaking the quadratic barrier: modern alternatives to softmax attention
Deeper is better: Coding ResNet from scratch Permalink
less than 1 minute read
Simple implementation of ResNet-50 from scratch using pytorch
Random Forest & AdaBoost: Coding Ensemble Methods from Scratch Permalink
less than 1 minute read
Simple implementation of Random Forest & AdaBoost(SAMME)