HYDesmondLiu

ESRL

Code for Expert Supervised Reinforcement Learning

D4RL

A collection of reference environments for offline reinforcement learning

Academic-Open-Source-Tool-and-Contest-Winners

awesome-offline-rl

An index of algorithms for offline reinforcement learning (offline-rl)

B2RL

The First Open-Sourced Building Batch Reinforcement Learning Dataset

B2RL_benchmarks

def-to-gdsii

Magic VLSI layout tool def-to-gdsii flow

google-research

Google Research

RUBICON

A novel method to incorporate existing policy (Rule-based control) with Reinforcement Learning.

BCQ

Author's PyTorch implementation of BCQ for continuous and discrete actions

HYDesmondLiu/B2RL

The First Open-Sourced Building Batch Reinforcement Learning Dataset

HYDesmondLiu/def-to-gdsii

Magic VLSI layout tool def-to-gdsii flow

HYDesmondLiu/RUBICON

A novel method to incorporate existing policy (Rule-based control) with Reinforcement Learning.

HYDesmondLiu/B2RL_benchmarks

HYDesmondLiu/Academic-Open-Source-Tool-and-Contest-Winners

HYDesmondLiu/autokeras

Accessible AutoML for deep learning.

HYDesmondLiu/awesome-offline-rl

An index of algorithms for offline reinforcement learning (offline-rl)

HYDesmondLiu/google-research

Google Research

HYDesmondLiu/BCQ

Author's PyTorch implementation of BCQ for continuous and discrete actions

HYDesmondLiu/CSE12

HYDesmondLiu/ESRL

Code for Expert Supervised Reinforcement Learning

HYDesmondLiu/HYDesmondLiu.github.io

Github Pages template for academic personal websites, forked from mmistakes/minimal-mistakes

HYDesmondLiu/keras-applications

Reference implementations of popular deep learning models.

HYDesmondLiu/leetcode

Python & JAVA Solutions for Leetcode

HYDesmondLiu/MyWebsite

HYDesmondLiu/OpenROAD-Utilities

Open-sourced utilities for initial flow setup, calibration, and other user functions for OpenROAD project

HYDesmondLiu/SVM-Image-Classification

Image Classification with `sklearn.svm`

HYDesmondLiu/WISMAQ

Adaptive Policy Regularization for Offline-to-Online Reinforcement Learning via Weighted Increased Simple Moving Average Q-value