Offline Reinforcement Learning with Implicit Q-Learning

This repository contains the official implementation of Offline Reinforcement Learning with Implicit Q-Learning by Ilya Kostrikov, Ashvin Nair, and Sergey Levine.

If you use this code for your research, please consider citing the paper:

@article{kostrikov2021iql,
    title={Offline Reinforcement Learning with Implicit Q-Learning},
    author={Ilya Kostrikov and Ashvin Nair and Sergey Levine},
    year={2021},
    archivePrefix={arXiv},
    primaryClass={cs.LG}
}

How to run the code

Install dependencies

pip install -r requirements.txt

See instructions for CUDA.

Run training

Locomotion

python train_offline.py --env_name=halfcheetah-medium-expert-v2 --config=configs/mujoco_config.py

AntMaze

python train_offline.py --env_name=antmaze-large-play-v0 --config=configs/antmaze_config.py --eval_episodes=100 --eval_interval=100000

Kitchen and Adroit

python train_offline.py --env_name=pen-human-v0 --config=configs/kitchen_config.py

Misc

The implementation is based on JAXRL.

Offline Reinforcement Learning with Implicit Q-Learning

Related tags

Overview

Offline Reinforcement Learning with Implicit Q-Learning

How to run the code

Install dependencies

Run training

Misc

Owner

Ilya Kostrikov

Codes for paper "KNAS: Green Neural Architecture Search"

Tutel MoE: An Optimized Mixture-of-Experts Implementation

A MatConvNet-based implementation of the Fully-Convolutional Networks for image segmentation

A lossless neural compression framework built on top of JAX.

Part-aware Measurement for Robust Multi-View Multi-Human 3D Pose Estimation and Tracking

Sound Source Localization for AI Grand Challenge 2021

source code of Adversarial Feedback Loop Paper

Definition of a business problem according to Wilson Lower Bound Score and Time Based Average Rating

Implementation of "A Deep Learning Loss Function based on Auditory Power Compression for Speech Enhancement" by pytorch

Tensorflow python implementation of "Learning High Fidelity Depths of Dressed Humans by Watching Social Media Dance Videos"

LRBoost is a scikit-learn compatible approach to performing linear residual based stacking/boosting.

CLNTM - Contrastive Learning for Neural Topic Model

Dashboard for the COVID19 spread

The implemetation of Dynamic Nerual Garments proposed in Siggraph Asia 2021

The Python code for the paper A Hybrid Quantum-Classical Algorithm for Robust Fitting

Compartmental epidemic model to assess undocumented infections: applications to SARS-CoV-2 epidemics in Brazil - Datasets and Codes

Pytorch-diffusion - A basic PyTorch implementation of 'Denoising Diffusion Probabilistic Models'

Learning Off-Policy with Online Planning, CoRL 2021

(under submission) Bayesian Integration of a Generative Prior for Image Restoration

Multispectral Object Detection with Yolov5