Generalized Decision Transformer for Offline Hindsight Information Matching

If you use this codebase for your research, please cite the paper:

@article{furuta2021generalized,
  title={Generalized Decision Transformer for Offline Hindsight Information Matching},
  author={Hiroki Furuta and Yutaka Matsuo and Shixiang Shane Gu},
  journal={arXiv preprint arXiv:2111.10364},
  year={2021}
}

Installation

Experiments require MuJoCo. Follow the instructions in the mujoco-py repo to install. Then, dependencies can be installed with the following command:

conda env create -f conda_env.yml

Downloading datasets

Datasets are stored in the data directory. Install the D4RL repo, following the instructions there. Then, run the following script in order to download the datasets and save them in our format:

python download_d4rl_datasets.py

Run experiments

Run train_cdt.py to train Categorical DT:

python train_cdt.py --env halfcheetah --dataset medium-expert --gpu 0 --seed 0 --dist_dim 30 --n_bins 31 --condition 'reward' --save_model True

python train_cdt.py --env halfcheetah --dataset medium-expert --gpu 0 --seed 0 --dist_dim 30 --n_bins 31 --condition 'xvel' --save_model True

Run eval_cdt.py to eval CDT using saved weights:

python eval_cdt.py --env halfcheetah --dataset medium-expert --gpu 0 --seed 0 --dist_dim 30 --n_bins 31 --condition 'reward' --save_rollout True
python eval_cdt.py --env halfcheetah --dataset medium-expert --gpu 0 --seed 0 --dist_dim 30 --n_bins 31 --condition 'xvel' --save_rollout True

For Bi-directional DT, run train_bdt.py & eval_bdtf.py

python train_bdt.py --env halfcheetah --dataset medium-expert --gpu 0 --seed 0 --dist_dim 30 --n_bins 31 --z_dim 16 --save_model True
python eval_bdt.py --env halfcheetah --dataset medium-expert --gpu 0 --seed 0 --dist_dim 30 --n_bins 31 --z_dim 16 --save_rollout True

Reference

This repository is developed on top of original Decision Transformer.

Generalized Decision Transformer for Offline Hindsight Information Matching

Related tags

Overview

Generalized Decision Transformer for Offline Hindsight Information Matching

Installation

Downloading datasets

Run experiments

Reference

Owner

Hiroki Furuta

This is the repository of shape matching algorithm Iterative Rotations and Assignments (IRA)

BoxInst: High-Performance Instance Segmentation with Box Annotations

This repository contains a PyTorch implementation of the paper Learning to Assimilate in Chaotic Dynamical Systems.

This is the codebase for Diffusion Models Beat GANS on Image Synthesis.

This is the reference implementation for "Coresets via Bilevel Optimization for Continual Learning and Streaming"

Official repository for the paper "GN-Transformer: Fusing AST and Source Code information in Graph Networks".

Code for SIMMC 2.0: A Task-oriented Dialog Dataset for Immersive Multimodal Conversations

Playable Video Generation

Employs neural networks to classify images into four categories: ship, automobile, dog or frog

Official Repsoitory for "Activate or Not: Learning Customized Activation." [CVPR 2021]

official implemntation for "Contrastive Learning with Stronger Augmentations"

Think Big, Teach Small: Do Language Models Distil Occam’s Razor?

Towards Rolling Shutter Correction and Deblurring in Dynamic Scenes (CVPR2021)

Using Machine Learning to Test Causal Hypotheses in Conjoint Analysis

PyTorch implementation HoroPCA: Hyperbolic Dimensionality Reduction via Horospherical Projections

QuakeLabeler is a Python package to create and manage your seismic training data, processes, and visualization in a single place — so you can focus on building the next big thing.

Official page of Struct-MDC (RA-L'22 with IROS'22 option); Depth completion from Visual-SLAM using point & line features

Oriented Object Detection: Oriented RepPoints + Swin Transformer/ReResNet

Object classification with basic computer vision techniques

Pytorch code for paper "Image Compressed Sensing Using Non-local Neural Network" TMM 2021.