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

A small demonstration of using WebDataset with ImageNet and PyTorch Lightning

SPTAG: A library for fast approximate nearest neighbor search

An Approach to Explore Logistic Regression Models

Code release to accompany paper "Geometry-Aware Gradient Algorithms for Neural Architecture Search."

Covid-19 Test AI (Deep Learning - NNs) Software. Accuracy is the %96.5, loss is the 0.09 :)

Example scripts for the detection of lanes using the ultra fast lane detection model in Tensorflow Lite.

Underwater industrial application yolov5m6

Implementation of paper "DeepTag: A General Framework for Fiducial Marker Design and Detection"

PyTorch framework, for reproducing experiments from the paper Implicit Regularization in Hierarchical Tensor Factorization and Deep Convolutional Neural Networks

Pre-trained models for a Cascaded-FCN in caffe and tensorflow that segments

SlotRefine: A Fast Non-Autoregressive Model forJoint Intent Detection and Slot Filling

Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering

Negative Sample Matters: A Renaissance of Metric Learning for Temporal Grounding

Code for Contrastive-Geometry Networks for Generalized 3D Pose Transfer

CLIP-GEN: Language-Free Training of a Text-to-Image Generator with CLIP

Implementation of Convolutional enhanced image Transformer

Artificial Intelligence playing minesweeper 🤖

Vrcwatch - Supply the local time to VRChat as Avatar Parameters through OSC

To model the probability of a soccer coach leave his/her team during Campeonato Brasileiro for 10 chosen teams and considering years 2018, 2019 and 2020.

Solving SMPL/MANO parameters from keypoint coordinates.