minhyuk-autonomouscar

Safe-MBPO

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

safety_rl

hj_reachability

Hamilton-Jacobi reachability analysis in JAX.

Safe-PDP

Safe Pontryagin Differentiable Programming (Safe PDP) is a new theoretical and algorithmic safe differentiable framework to solve a broad class of safety-critical learning and control tasks.

Safe-Reinforcement-Learning-Baselines

The repository is for safe reinforcement learning baselines.

crabs

Code for Learning Barrier Certificates: Towards Safe Reinforcement Learning with Zero Training-time Violations

Mod-RL-RCBF

maddpg-pytorch

PyTorch Implementation of MADDPG (Lowe et. al. 2017)

deepreach

NeuralVerification.jl

Methods to soundly verify deep neural networks

NNDM-safe-control

UPDeT

Official Implementation of 'UPDeT: Universal Multi-agent Reinforcement Learning via Policy Decoupling with Transformers' ICLR 2021(spotlight)

multiagent_mujoco

Benchmark for Continuous Multi-Agent Robotic Control, based on OpenAI's Mujoco Gym environments.

TRPO-in-MARL

gym-carla

An OpenAI gym wrapper for CARLA simulator

RandUP

A Simple and Efficient Sampling-based Algorithm for General Reachability Analysis

ISSA_CoRL21

KoopmanMPC

model-predictive-shielding

macad-gym

Multi-Agent Connected Autonomous Driving (MACAD) Gym environments for Deep RL. Code for the paper presented in the Machine Learning for Autonomous Driving Workshop at NeurIPS 2019:

carla

Open-source simulator for autonomous driving research.

pyadrc

Active Disturbance Rejection Control for Python

Recurrent-Multiagent-Deep-Deterministic-Policy-Gradient-with-Difference-Rewards

Deep Reinforcement Learning (DRL) algorithms have been successfully applied to a range of challenging simulated continuous control single agent tasks. These methods have further been extended to multiagent domains in cooperative, competitive or mixed environments. This paper primarily focuses on multiagent cooperative settings which can be modeled for several real world problems such as coordination of autonomous vehicles and warehouse robots. However, these systems suffer from several challenges such as, structural credit assignment and partial observability. In this paper, we propose Recurrent Multiagent Deep Deterministic Policy Gradient (RMADDPG) algorithm which extends Multiagent Deep Determinisitic Policy Gradient algorithm - MADDPG \cite{lowe2017multi} by using a recurrent neural network for the actor policy. This helps to address partial observability by maintaining a sequence of past observations which networks learn to preserve in order to solve the POMDP. In addition, we use reward shaping through difference rewards to address structural credit assignment in a partially observed environment. We evaluate the performance of MADDPG and R-MADDPG with and without reward shaping in a Multiagent Particle Environment. We further show that reward shaped RMADDPG outperforms the baseline algorithm MADDPG in a partially observable environmental setting.

SAC-RCBF

geoopt

Riemannian Adaptive Optimization Methods with pytorch optim

safe-control-gym

PyBullet CartPole and Quadrotor environments—with CasADi symbolic a priori dynamics—for learning-based control and RL

optimized_dp

Optimizing Dynamic Programming-Based Algorithms

DeepReinforcementLearningInAction

Code from the Deep Reinforcement Learning in Action book from Manning, Inc

AirLearning

Public repository for Air Learning project

BaRC

Contains the code for "BaRC: Backward Reachability Curriculum for Robotic Reinforcement Learning" by Boris Ivanovic, James Harrison, Apoorva Sharma, Mo Chen, Marco Pavone.