Lipschitz-constrained Unsupervised Skill Discovery

This repository is the official implementation of

Seohong Park, Jongwook Choi*, Jaekyeom Kim*, Honglak Lee, Gunhee Kim (*: equal contribution). Lipschitz-constrained Unsupervised Skill Discovery. In ICLR, 2022. [paper] [project page] [slides]

The implementation is based on Unsupervised Skill Discovery with Bottleneck Option Learning and garage.

Visit our project page for more results including videos.

Requirements

Python 3.7.8
MuJoCo 1.5

Examples

Install requirements:

pip install -r requirements.txt
pip install -e .
pip install -e garaged

Ant with 2-D continuous skills:

python tests/main.py --run_group EXP --env ant --max_path_length 200 --dim_option 2 --common_lr 0.0001 --seed 0 --normalizer_type ant_preset --use_gpu 1 --traj_batch_size 20 --n_parallel 8 --n_epochs_per_eval 5000 --n_thread 1 --model_master_dim 1024 --record_metric_difference 0 --n_epochs_per_tb 100 --n_epochs_per_save 50000 --n_epochs_per_pt_save 5000 --n_epochs_per_pkl_update 1000 --eval_record_video 1 --n_epochs 200001 --spectral_normalization 1 --n_epochs_per_log 50 --discrete 0 --num_random_trajectories 200 --sac_discount 0.99 --alpha 0.01 --sac_lr_a -1 --lr_te 3e-05 --sac_scale_reward 0 --max_optimization_epochs 1 --trans_minibatch_size 2048 --trans_optimization_epochs 4 --eval_plot_axis -50 50 -50 50

Ant with 16 discrete skills:

python tests/main.py --run_group EXP --env ant --max_path_length 200 --dim_option 16 --common_lr 0.0001 --seed 0 --normalizer_type ant_preset --use_gpu 1 --traj_batch_size 20 --n_parallel 8 --n_epochs_per_eval 5000 --n_thread 1 --model_master_dim 1024 --record_metric_difference 0 --n_epochs_per_tb 100 --n_epochs_per_save 50000 --n_epochs_per_pt_save 5000 --n_epochs_per_pkl_update 1000 --eval_record_video 1 --n_epochs 200001 --spectral_normalization 1 --n_epochs_per_log 50 --discrete 1 --num_random_trajectories 200 --sac_discount 0.99 --alpha 0.003 --sac_lr_a -1 --lr_te 3e-05 --sac_scale_reward 0 --max_optimization_epochs 1 --trans_minibatch_size 2048 --trans_optimization_epochs 4 --eval_plot_axis -50 50 -50 50

Humanoid with 2-D continuous skills:

python tests/main.py --run_group EXP --env humanoid --max_path_length 1000 --dim_option 2 --common_lr 0.0003 --seed 0 --normalizer_type humanoid_preset --use_gpu 1 --traj_batch_size 5 --n_parallel 8 --n_epochs_per_eval 5000 --n_thread 1 --model_master_dim 1024 --record_metric_difference 0 --n_epochs_per_tb 100 --n_epochs_per_save 50000 --n_epochs_per_pt_save 5000 --n_epochs_per_pkl_update 1000 --eval_record_video 1 --n_epochs 200001 --spectral_normalization 1 --n_epochs_per_log 50 --discrete 0 --video_skip_frames 3 --num_random_trajectories 200 --sac_discount 0.99 --alpha 0.03 --sac_lr_a -1 --lr_te 0.0001 --lsd_alive_reward 0.03 --sac_scale_reward 0 --max_optimization_epochs 1 --trans_minibatch_size 2048 --trans_optimization_epochs 4 --sac_replay_buffer 1 --te_max_optimization_epochs 1 --te_trans_optimization_epochs 2

Humanoid with 16 discrete skills:

python tests/main.py --run_group EXP --env humanoid --max_path_length 1000 --dim_option 16 --common_lr 0.0003 --seed 0 --normalizer_type humanoid_preset --use_gpu 1 --traj_batch_size 5 --n_parallel 8 --n_epochs_per_eval 5000 --n_thread 1 --model_master_dim 1024 --record_metric_difference 0 --n_epochs_per_tb 100 --n_epochs_per_save 50000 --n_epochs_per_pt_save 5000 --n_epochs_per_pkl_update 1000 --eval_record_video 1 --n_epochs 200001 --spectral_normalization 1 --n_epochs_per_log 50 --discrete 1 --video_skip_frames 3 --num_random_trajectories 200 --sac_discount 0.99 --alpha 0.03 --sac_lr_a -1 --lr_te 0.0001 --lsd_alive_reward 0.03 --sac_scale_reward 0 --max_optimization_epochs 1 --trans_minibatch_size 2048 --trans_optimization_epochs 4 --sac_replay_buffer 1 --te_max_optimization_epochs 1 --te_trans_optimization_epochs 2

HalfCheetah with 8 discrete skills:

python tests/main.py --run_group EXP --env half_cheetah --max_path_length 200 --dim_option 8 --common_lr 0.0001 --seed 0 --normalizer_type half_cheetah_preset --use_gpu 1 --traj_batch_size 20 --n_parallel 8 --n_epochs_per_eval 5000 --n_thread 1 --model_master_dim 1024 --record_metric_difference 0 --n_epochs_per_tb 100 --n_epochs_per_save 50000 --n_epochs_per_pt_save 5000 --n_epochs_per_pkl_update 1000 --eval_record_video 1 --n_epochs 200001 --spectral_normalization 1 --n_epochs_per_log 50 --discrete 1 --num_random_trajectories 200 --sac_discount 0.99 --alpha 0.01 --sac_lr_a -1 --lr_te 3e-05 --sac_scale_reward 0 --max_optimization_epochs 1 --trans_minibatch_size 2048 --trans_optimization_epochs 4

Lipschitz-constrained Unsupervised Skill Discovery

Related tags

Overview

Lipschitz-constrained Unsupervised Skill Discovery

Requirements

Examples

Owner

Seohong Park

Working demo of the Multi-class and Anomaly classification model using the CLIP feature space

Multi-Scale Vision Longformer: A New Vision Transformer for High-Resolution Image Encoding

Semi-Supervised Learning with Ladder Networks in Keras. Get 98% test accuracy on MNIST with just 100 labeled examples !

The repository for the paper "When Do You Need Billions of Words of Pretraining Data?"

QAT(quantize aware training) for classification with MQBench

Count the MACs / FLOPs of your PyTorch model.

Demystifying How Self-Supervised Features Improve Training from Noisy Labels

Boostcamp AI Tech 3rd / Basic Paper reading w.r.t Embedding

Generic Foreground Segmentation in Images

Cryptocurrency Prediction with Artificial Intelligence (Deep Learning via LSTM Neural Networks)

Human Action Controller - A human action controller running on different platforms.

This is the official code for the paper "Tracker Meets Night: A Transformer Enhancer for UAV Tracking".

PyTorch implementation of the Transformer in Post-LN (Post-LayerNorm) and Pre-LN (Pre-LayerNorm).

Image super-resolution (SR) is a fast-moving field with novel architectures attracting the spotlight

This repo holds code for TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation

Official implementation for paper: A Latent Transformer for Disentangled Face Editing in Images and Videos.

🔮 Execution time predictions for deep neural network training iterations across different GPUs.

Pytorch implementation for "Density-aware Chamfer Distance as a Comprehensive Metric for Point Cloud Completion" (NeurIPS 2021)

Camera-caps - Examine the camera capabilities for V4l2 cameras

AAAI 2022 paper - Unifying Model Explainability and Robustness for Joint Text Classification and Rationale Extraction