zzjun725

LipsNet

LipsNet: A Smooth and Robust Neural Network with Adaptive Lipschitz Constant for High Accuracy Optimal Control (ICML 2023)

contrastive_loss

Experiments with supervised contrastive learning methods with different loss functions

Safe-MBPO

Code for the NeurIPS 2021 paper "Safe Reinforcement Learning by Imagining the Near Future"

awesome-model-based-RL

A curated list of awesome model based RL resources (continually updated)

dreamerv3-torch

Implementation of Dreamer v3 in pytorch.

Pearl

A Production-ready Reinforcement Learning AI Agent Library brought by the Applied Reinforcement Learning team at Meta.

rl

A modular, primitive-first, python-first PyTorch library for Reinforcement Learning.

spinningup

An educational resource to help anyone learn deep reinforcement learning.

f1tenth_racetracks

This repository contains maps from over 20 real race tracks (mainly F1 and DTM) downscaled for the usage in the F1TENTH Gym and F1TENTH Simulator.

rl_games

RL implementations

f1tenth_benchmarks

Implementations of common F1Tenth autonomous racing algorithms with benchmark results.

NeuralNetwork_for_VehicleDynamicsModeling

Multi-Agent-VQA

Multi-Agent VQA: Exploring Multi-Agent Foundation Models on Zero-Shot Visual Question Answering

rlpyt

Reinforcement Learning in PyTorch

adversarial_comms

graph-conv-memory-paper

Graph convolutional memory for reinforcement learning

ODE2VAE

ODE2VAE: Deep generative second order ODEs with Bayesian neural networks

HILP

Foundation Policies with Hilbert Representations (ICML 2024)

differentiable-mpc

cleanrl

High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)

learning_adaptive_safety

Repository of the work "Learning Adaptive Safety for Multi-agent Systems"

Training-Overtaking-Algorithm

This repository has code of how to train a RNN that can perform overtaking in F1TENTH simulator as well as a dataset I have created

PIT

Physics-informed toolbox

f1tenth_planning

Central repo for all motion planners created for F1TENTH.

LLaVA

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

race_stack

The autonomous racing stack for the ForzaETH team at PBL

frenet

Transform Frenet (s,d) to local Cartesian (x,y) coordinates.

GraphBasedLocalTrajectoryPlanner

Local trajectory planner based on a multilayer graph framework for autonomous race vehicles.

trajectory_planning_helpers

Useful functions used for path and trajectory planning at TUM/FTM

DiffProj

End-to-End Learning of Behavioural Inputs for Autonomous Driving in Dense Traffic