• Stars
    star
    125
  • Rank 286,335 (Top 6 %)
  • Language
    Python
  • Created about 7 years ago
  • Updated over 2 years ago

Reviews

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Repository Details

2nd place solution of NIPS2017 LearningToRun Competition.

NIPS2017-LearningToRun with ACE

Zhewei Huang, Shuchang Zhou, BoEr Zhuang, Xinyu Zhou

Demo

A keras solution for 2nd place NIPS RL 2017 challenge.

There is a slide, a lecture and a writeup(arxiv) about our work.

To Run

preparation

These instructions expect that opensim-rl conda environment is already setup as described in : https://github.com/stanfordnmbl/osim-rl/ .

$ source activate opensim-rl

Other dependencies is needed as follow

  • Keras(since old version does not support selu activation)
  • TensorFlow
  • matplotlib
  • numpy
  • Pyro4
  • parse
  • pymsgbox(optional)

parallelism

This version requires farming, before starting train.py, you should first start some farms by running python farm.py on each SLAVE machine you own. Then create a farmlist.py in the working directory (on the HOST machine) with the following content :

farmlist_base = [('127.0.0.1', 4), ('192.168.1.1', 8)]

# a farm of 4 cores is available on localhost, while a farm of 8 is available on another machine.

# expand the list if you have more machines.

# this file will be consumed by the host to find the slaves.

Try python farm.py --help to get more information about how to set the environment.

More information can be found in https://github.com/ctmakro/stanford-osrl .

Thanks to @ctmakro for providing us with this frame.

test

Test the model in parallel and calculate the average score.

We provide you with some trained parameters.

python test.py -a=10 -c=5 -t=200 -p logs

# test the model for 200 times with 10 actor networks and 5 critic networks ensemble

# the network parameters should be placed as logs/actormodel1.h5 ... logs/actormodel10.h5

Try python test.py --help to get more information .

Contributors

Resources

More Repositories

1

ECCV2022-RIFE

ECCV2022 - Real-Time Intermediate Flow Estimation for Video Frame Interpolation
Python
4,075
star
2

shareOI

็ฎ—ๆณ•็ซž่ต›่ฏพไปถๅˆ†ไบซ
3,714
star
3

ICCV2019-LearningToPaint

ICCV2019 - Learning to Paint With Model-based Deep Reinforcement Learning
Python
2,228
star
4

WritingAIPaper

Writing AI Conference Papers: A Handbook for Beginners
1,134
star
5

Practical-RIFE

We are developing more practical approach for users based on RIFE.
Python
438
star
6

Awesome-Optical-Flow

This is a list of awesome paper about optical flow and related work.
349
star
7

CVPR2023-DMVFN

CVPR2023 (highlight) - A Dynamic Multi-Scale Voxel Flow Network for Video Prediction
Jupyter Notebook
316
star
8

WACV2024-SAFA

WACV2024 - Scale-Adaptive Feature Aggregation for Efficient Space-Time Video Super-Resolution
Python
95
star
9

termdic

Dictionary in your terminal
Python
52
star
10

MM2022-ViCoPerceptualHeadGeneration

MM2022 Workshop-Perceptual Conversational Head Generation with Regularized Driver and Enhanced Renderer
Python
49
star
11

NeurIPS2021-ML4CO-KIDA

1st Solution For NeurIPS 2021 Competition on ML4CO Dual Task
Python
27
star
12

brief_paper_reading

My paper reading and insights record
Python
21
star
13

AML

Agent Manipulation Language
C++
17
star
14

Stroke-basedCharacterReconstruction

Stroke-based Character Reconstruction ---> https://arxiv.org/abs/1806.08990
Python
15
star
15

MFSR-TSM

Multi-Frame Super-Resolution based on Temporal Shift Module
Python
9
star
16

ResynNet

Refine video frame based on nearby frames.
Python
7
star
17

hzwer

7
star