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

Pytorch implementation for Semantic Segmentation/Scene Parsing on MIT ADE20K dataset

Foreground-Action Consistency Network for Weakly Supervised Temporal Action Localization

Implementation for our ICCV 2021 paper: Dual-Camera Super-Resolution with Aligned Attention Modules

Hierarchical Few-Shot Generative Models

Type4Py: Deep Similarity Learning-Based Type Inference for Python

Simple keras FCN Encoder/Decoder model for MS-COCO (food subset) segmentation

🎓Automatically Update CV Papers Daily using Github Actions (Update at 12:00 UTC Every Day)

Multi-Object Tracking in Satellite Videos with Graph-Based Multi-Task Modeling

A modification of Daniel Russell's notebook merged with Katherine Crowson's hq-skip-net changes

Use deep learning, genetic programming and other methods to predict stock and market movements

This is the official implementation for "Do Transformers Really Perform Bad for Graph Representation?".

GPU Accelerated Non-rigid ICP for surface registration

This is a Pytorch implementation of paper: DropEdge: Towards Deep Graph Convolutional Networks on Node Classification

MLPs for Vision and Langauge Modeling (Coming Soon)

This library provides an abstraction to perform Model Versioning using Weight & Biases.

Translate darknet to tensorflow. Load trained weights, retrain/fine-tune using tensorflow, export constant graph def to mobile devices

Official Codes for Graph Modularity:Towards Understanding the Cross-Layer Transition of Feature Representations in Deep Neural Networks.

A simple Python configuration file operator.

Boosted CVaR Classification (NeurIPS 2021)

PICK: Processing Key Information Extraction from Documents using Improved Graph Learning-Convolutional Networks