jieli18 Goto Github PK

admrl

Code for paper "Model-based Adversarial Meta-Reinforcement Learning" (https://arxiv.org/abs/2006.08875)

atla_robust_rl

Robust Reinforcement Learning with the Alternating Training of Learned Adversaries (ATLA) framework

bcq

Author's PyTorch implementation of BCQ for continuous and discrete actions

bigan

code for "Adversarial Feature Learning"

cdcs

An open-source MATLAB® ADMM solver for partially decomposable conic optimization programs.

distributional-soft-actor-critic

docs

TensorFlow documentation

gym-adv

Gym environments modified with adversarial agents

hamiltonian-nn

Code for our paper "Hamiltonian Neural Networks"

handful-of-trials

Experiment code for "Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models"

jieli18.github.io

mbpo

Code for the paper "When to Trust Your Model: Model-Based Policy Optimization"

mcnpytorch

Model converter (PyTorch -> MatConvNet)

minimal-isaac-gym

A Minimal Example of Isaac Gym with DQN and PPO.

ml_pytorch

oyster

Implementation of Efficient Off-policy Meta-learning via Probabilistic Context Variables (PEARL)

parl

A high-performance distributed training framework for Reinforcement Learning

pomdp-baselines

Simple (but often Strong) Baselines for POMDPs in PyTorch - ICML 2022

pontryagin-differentiable-programming

A unified end-to-end learning and control framework that is able to learn a (neural) control objective function, dynamics equation, control policy, or/and optimal trajectory in a control system.

projects_participated

pytorch-spectral-normalization-gan

Paper by Miyato et al. https://openreview.net/forum?id=B1QRgziT-

radial_rl_v2

This repository contains the official code for our NeurIPS 2021 publication "Robust Deep Reinforcement Learning through Adversarial Loss​"

rambo

Robust Adversarial Model-Based Offline RL

rl-scpo

The code of paper *Learning Robust Policy against Disturbance in Transition Dynamics via State-Conservative Policy Optimization*.

rllab-adv

Code to train RL agents along with Adversarial distrubance agents

robust_rl_multi_adversary

We investigate the effect of populations on finding good solutions to the robust MDP

sa_ddpg

[NeurIPS 2020 Spotlight] State-adversarial DDPG for robust deep reinforcement learning

sa_ppo

State-adversarial PPO for robust deep reinforcement learning

safe-mbpo

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

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.