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

An open framework for Federated Learning.

Code for the paper "M2m: Imbalanced Classification via Major-to-minor Translation" (CVPR 2020)

DARTS-: Robustly Stepping out of Performance Collapse Without Indicators

implement of SwiftNet:Real-time Video Object Segmentation

[Pedestron] Generalizable Pedestrian Detection: The Elephant In The Room. @ CVPR2021

Real-time pose estimation accelerated with NVIDIA TensorRT

Transfer Reinforcement Learning for Differing Action Spaces via Q-Network Representations

This computer program provides a reference implementation of Lagrangian Monte Carlo in metric induced by the Monge patch

a spacial-temporal pattern detection system for home automation

This is the second place solution for : UmojaHack Africa 2022: African Snake Antivenom Binding Challenge

Bot developed in Python that automates races in pegaxy.

Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context Code in both PyTorch and TensorFlow

Research code of ICCV 2021 paper "Mesh Graphormer"

Image De-raining Using a Conditional Generative Adversarial Network

Materials for my scikit-learn tutorial

Code for models used in Bashiri et al., "A Flow-based latent state generative model of neural population responses to natural images".

Parametric Contrastive Learning (ICCV2021)

Unofficial implement with paper SpeakerGAN: Speaker identification with conditional generative adversarial network

The pure and clear PyTorch Distributed Training Framework.

Deep Reinforcement Learning for Keras.