laijiajian

bluesky

The open source air traffic simulator

carla-driving-rl-agent

Code for the paper "Reinforced Curriculum Learning for Autonomous Driving in CARLA" (ICIP 2021)

ChauffeurNet

CQL

Conservative Q Learning on top of SAC

crl_kino

Using RL based controller for steering function of RRT. And a network learns to perform motion planning

FCN8s-PyTorch

just a practice

lets-do-irl

Inverse RL algorithms (APP, MaxEnt, GAIL, VAIL)

Meta-Learning-for-StarCraft-II-Minigames

We reproduced DeepMind's results and implement a meta-learning (MLSH) agent which can generalize across minigames.

mujoco-py

MuJoCo is a physics engine for detailed, efficient rigid body simulations with contacts. mujoco-py allows using MuJoCo from Python 3.

Multi-Agent-Transformer

laijiajian/CQL

Conservative Q Learning on top of SAC

laijiajian/bluesky

The open source air traffic simulator

laijiajian/carla-driving-rl-agent

Code for the paper "Reinforced Curriculum Learning for Autonomous Driving in CARLA" (ICIP 2021)

laijiajian/ChauffeurNet

laijiajian/crl_kino

Using RL based controller for steering function of RRT. And a network learns to perform motion planning

laijiajian/FCN8s-PyTorch

just a practice

laijiajian/lets-do-irl

Inverse RL algorithms (APP, MaxEnt, GAIL, VAIL)

laijiajian/Meta-Learning-for-StarCraft-II-Minigames

We reproduced DeepMind's results and implement a meta-learning (MLSH) agent which can generalize across minigames.

laijiajian/mujoco-py

MuJoCo is a physics engine for detailed, efficient rigid body simulations with contacts. mujoco-py allows using MuJoCo from Python 3.

laijiajian/Multi-Agent-Transformer

laijiajian/PPO-PyTorch

Minimal implementation of clipped objective Proximal Policy Optimization (PPO) in PyTorch

laijiajian/RVO_Py_MAS

Python Implementation of Reciprocal Velocity Obstacle for Multi-agent Systems

laijiajian/Safe-Policy-Optimization

This is a benchmark repository for safe reinforcement learning algorithms

laijiajian/Safe-Reinforcement-Learning-Baselines

The repository is for safe reinforcement learning baselines.