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

Implementation of paper: "Image Super-Resolution Using Dense Skip Connections" in PyTorch

Code for "Adversarial Training for a Hybrid Approach to Aspect-Based Sentiment Analysis

Iterative Training: Finding Binary Weight Deep Neural Networks with Layer Binarization

A rough implementation of the paper "A Steering Algorithm for Redirected Walking Using Reinforcement Learning"

A PyTorch implementation of the continual learning experiments with deep neural networks

Mahadi-Now - This Is Pakistani Just Now Login Tools

A Topic Modeling toolbox

Python package provinding tools for artistic interactive applications using AI

A semantic segmentation toolbox based on PyTorch

This repo contains the pytorch implementation for Dynamic Concept Learner (accepted by ICLR 2021).

Pytorch implementation of Make-A-Scene: Scene-Based Text-to-Image Generation with Human Priors

MM1 and MMC Queue Simulation using python - Results and parameters in excel and csv files

MINIROCKET: A Very Fast (Almost) Deterministic Transform for Time Series Classification

First-Order Probabilistic Programming Language

For encoding a text longer than 512 tokens, for example 800. Set max_pos to 800 during both preprocessing and training.

The devkit of the nuScenes dataset.

vit for few-shot classification

An efficient PyTorch implementation of the evaluation metrics in recommender systems.

Deep Learning for Human Part Discovery in Images - Chainer implementation

GE2340 project source code without credentials.