hemerson1 Goto Github PK

agentrl

A package containing several significant or innovative reinforcement learning algorithms with a focus on easy integration.

blog-code

decision-transformer

Official codebase for Decision Transformer: Reinforcement Learning via Sequence Modeling.

deep-rl-intro

A collection of the projects done alongside the 2020 Berkeley Deep RL course CS285.

gchelper

A set of functions used for data collection, testing and visualisation with the UVA/Padova T1D simulator.

hemerson1.github.io

mcts-checkers

An implementation of Monte-Carlo-Tree-Search for learning to play the board game Checkers through self-play.

offline-glucose

The code release for "Offline Reinforcement Learning for Safer Blood Glucose Control in People with Type 1 Diabetes".

openaps_cleaner

Package for processing the OpenAPS Data Commons into a machine learning compatible format.

popular-rl-algorithms

PyTorch implementation of Soft Actor-Critic (SAC), Twin Delayed DDPG (TD3), Actor-Critic (AC/A2C), Proximal Policy Optimization (PPO), QT-Opt, PointNet..

rldevelopment

A small package of useful functions for prototyping offline RL algorithms.

rltheory

From scratch implementations of machine learning, deep learning and reinforcement learning algorithms.

simglucose

A Type-1 Diabetes simulator implemented in Python for Reinforcement Learning purpose.

simplerl

A package containing several lightweight reinforcement learning environments.

trajectory-transformer

Code for the paper "Offline Reinforcement Learning as One Big Sequence Modeling Problem"