Stars
One repository is all that is necessary for Multi-agent Reinforcement Learning (MARL)
Python Implementation of Reciprocal Velocity Obstacle for Multi-agent Systems
Source code for the dissertation: "Multi-Pass Deep Q-Networks for Reinforcement Learning with Parameterised Action Spaces"
An artificial intelligence platform for the StarCraft II with large-scale distributed training and grand-master agents.
OpenDILab Decision AI Engine. The Most Comprehensive Reinforcement Learning Framework B.P.
Classification of Time-series data with RNN
[CoRL'20] Learning a Decision Module by Imitating Driver’s Control Behaviors
Scalable Multi-Agent RL Training School for Autonomous Driving
NeurIPS 2023: Safe Policy Optimization: A benchmark repository for safe reinforcement learning algorithms
Train an autonomous vehicle by CNN deep learning to drive like humans
laijiajian / CQL
Forked from young-geng/CQLConservative Q Learning on top of SAC
Inverse RL algorithms (APP, MaxEnt, GAIL, VAIL)
Code for the paper "Reinforced Curriculum Learning for Autonomous Driving in CARLA" (ICIP 2021)
Reinforcement learning for an air traffic control task. OpenAI gym based simulation.
openScope Air Traffic Control Simulator
Basic constrained RL agents used in experiments for the "Benchmarking Safe Exploration in Deep Reinforcement Learning" paper.
The repository is for safe reinforcement learning baselines.
Using RL based controller for steering function of RRT. And a network learns to perform motion planning
Simulink/Matlab model of linear and nonlinear flight controller for Boeing 747.
强化学习中文教程（蘑菇书🍄），在线阅读地址：https://datawhalechina.github.io/easy-rl/
OpenSpiel is a collection of environments and algorithms for research in general reinforcement learning and search/planning in games.
Python Version of F-16 Maneuver Verification Benchmark
Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.