OstrichRL: A Musculoskeletal Ostrich Simulation to Study Bio-mechanical Locomotion.

Last update: Nov 17, 2022

Related tags

Overview

OstrichRL

This is the repository accompanying the paper OstrichRL: A Musculoskeletal Ostrich Simulation to Study Bio-mechanical Locomotion.

It contains models of a musculoskeletal ostrich and of the Cassie robot, motion capture data, and tasks for the dm_control suite:

ostrich-run
ostrich-mocap_tracking
ostrich-foraging
ostrich-run_torque
cassie-run
cassie-mocap_tracking

Instructions

To install

Download and install OstrichRL:

git clone https://github.com/vittorione94/ostrichrl
pip install -e ostrichrl/

To launch experiments

We recommend using the Tonic RL library.

Download and install Tonic:

git clone https://github.com/fabiopardo/tonic
pip install -e tonic/

To play with the environments and random actions

python -m tonic.play --header "import ostrichrl" \
--env "tonic.environments.ControlSuite('ostrich-run')" \
--agent "tonic.agents.UniformRandom()"

python -m tonic.play --header "import ostrichrl" \
--env "tonic.environments.ControlSuite('ostrich-mocap_tracking', task_kwargs=dict(clip='cyclic', test=True, play=True))" \
--agent "tonic.agents.UniformRandom()"

python -m tonic.play --header "import ostrichrl" \
--env "tonic.environments.ControlSuite('ostrich-foraging')" \
--agent "tonic.agents.UniformRandom()"

python -m tonic.play --header "import ostrichrl" \
--env "tonic.environments.ControlSuite('ostrich-run_torque')" \
--agent "tonic.agents.UniformRandom()"

python -m tonic.play --header "import ostrichrl" \
--env "tonic.environments.ControlSuite('cassie-run')" \
--agent "tonic.agents.UniformRandom()"

python -m tonic.play --header "import ostrichrl" \
--env "tonic.environments.ControlSuite('cassie-mocap_tracking', task_kwargs=dict(clip='0100', test=True, play=True))" \
--agent "tonic.agents.UniformRandom()"

To train

python -m tonic.train --header "import ostrichrl, tonic.tensorflow" \
--env "tonic.environments.ControlSuite('ostrich-mocap_tracking', task_kwargs=dict(clip='0047'))" \
--test_env "tonic.environments.ControlSuite('ostrich-mocap_tracking', task_kwargs=dict(clip='0047', test=True))" \
--agent "tonic.tensorflow.agents.TD4()" \
--parallel 8 \
--sequential 5

OstrichRL: A Musculoskeletal Ostrich Simulation to Study Bio-mechanical Locomotion.

Related tags

Overview

OstrichRL

Instructions

To install

To launch experiments

To play with the environments and random actions

To train

Owner

Vittorio La Barbera

PaddleViT: State-of-the-art Visual Transformer and MLP Models for PaddlePaddle 2.0+

Implementations of paper Controlling Directions Orthogonal to a Classifier

Fast Axiomatic Attribution for Neural Networks (NeurIPS*2021)

GARCH and Multivariate LSTM forecasting models for Bitcoin realized volatility with potential applications in crypto options trading, hedging, portfolio management, and risk management

Implementation of H-Transformer-1D, Hierarchical Attention for Sequence Learning using 🤗 transformers

Tensorflow solution of NER task Using BiLSTM-CRF model with Google BERT Fine-tuning And private Server services

Implementation of the master's thesis "Temporal copying and local hallucination for video inpainting".

Help you understand Manual and w/ Clutch point while driving.

Code of paper Interact, Embed, and EnlargE (IEEE): Boosting Modality-specific Representations for Multi-Modal Person Re-identification.

Official Code for VideoLT: Large-scale Long-tailed Video Recognition (ICCV 2021)

Detecting Blurred Ground-based Sky/Cloud Images

一些经典的CTR算法的复现; LR, FM, FFM, AFM, DeepFM，xDeepFM, PNN, DCN, DCNv2, DIFM, AutoInt, FiBiNet,AFN,ONN,DIN, DIEN ... （pytorch, tf2.0）

A PyTorch implementation of "Semi-Supervised Graph Classification: A Hierarchical Graph Perspective" (WWW 2019)

Application of the L2HMC algorithm to simulations in lattice QCD.

Transfer SemanticKITTI labeles into other dataset/sensor formats.

Understanding and Improving Encoder Layer Fusion in Sequence-to-Sequence Learning (ICLR 2021)

Hitters Linear Regression - Hitters Linear Regression With Python

DeepFaceLab fork which provides IPython Notebook to use DFL with Google Colab

Spearmint Bayesian optimization codebase

C3DPO - Canonical 3D Pose Networks for Non-rigid Structure From Motion.