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

As-ViT: Auto-scaling Vision Transformers without Training

ArtEmis: Affective Language for Art

A Python package for causal inference using Synthetic Controls

A Deep Learning Based Knowledge Extraction Toolkit for Knowledge Base Population

Unofficial TensorFlow implementation of Protein Interface Prediction using Graph Convolutional Networks.

DeepProbLog is an extension of ProbLog that integrates Probabilistic Logic Programming with deep learning by introducing the neural predicate.

Pgn2tex - Scripts to convert pgn files to latex document. Useful to build books or pdf from pgn studies

A Convolutional Transformer for Keyword Spotting

[PyTorch] Official implementation of CVPR2021 paper "PointDSC: Robust Point Cloud Registration using Deep Spatial Consistency". https://arxiv.org/abs/2103.05465

An intuitive library to extract features from time series

Official Pytorch Implementation of GraphiT

Release of the ConditionalQA dataset

《Towards High Fidelity Face Relighting with Realistic Shadows》(CVPR 2021)

A JAX implementation of Broaden Your Views for Self-Supervised Video Learning, or BraVe for short.

Training Very Deep Neural Networks Without Skip-Connections

Gas detection for Raspberry Pi using ADS1x15 and MQ-2 sensors

A real-time approach for mapping all human pixels of 2D RGB images to a 3D surface-based model of the body

A simple rest api serving a deep learning model that classifies human gender based on their faces. (vgg16 transfare learning)

Multi-objective gym environments for reinforcement learning.

ChainerRL is a deep reinforcement learning library built on top of Chainer.