CURL: Contrastive Unsupervised Representation Learning for Sample-Efficient Reinforcement Learning
MishaLaskin/curl 排名第 16,186，有 607 个星标。
同类别比较
MishaLaskin/curl 排名第 16,186，此处有 8 个同类条目；theAIGuysCode/yolov4-custom-functions 排名第 16,182。
同类别比较| 名称 | 排名 | 指标 |
|---|
| benedekrozemberczki/GraphWaveletNeuralNetwork | 16,172 | - 语言:
- Python
- 星标数:
- 608
- 分叉数:
- 117
- 简介:
- A PyTorch implementation of "Graph Wavelet Neural Network" (ICLR 2019)
|
|---|
| google-research-datasets/dstc8-schema-guided-dialogue | 16,175 | - 语言:
- Python
- 星标数:
- 608
- 分叉数:
- 136
- 简介:
- The Schema-Guided Dialogue Dataset
|
|---|
| stefanopini/simple-HRNet | 16,180 | - 语言:
- Python
- 星标数:
- 608
- 分叉数:
- 111
- 简介:
- Multi-person Human Pose Estimation with HRNet in Pytorch
|
|---|
| theAIGuysCode/yolov4-custom-functions | 16,182 | - 语言:
- Python
- 星标数:
- 608
- 分叉数:
- 360
- 简介:
- A Wide Range of Custom Functions for YOLOv4, YOLOv4-tiny, YOLOv3, and YOLOv3-tiny Implemented in TensorFlow, TFLite, and TensorRT.
|
|---|
| wzdnzd/harvester | 16,193 | - 语言:
- Python
- 星标数:
- 607
- 分叉数:
- 136
- 简介:
- Intelligent data acquisition framework for GitHub and web sources
|
|---|
| EdGENetworks/attention-networks-for-classification | 16,196 | - 语言:
- Jupyter Notebook
- 星标数:
- 606
- 分叉数:
- 130
- 简介:
- Hierarchical Attention Networks for Document Classification in PyTorch
|
|---|
| levyflux/AViD | 16,205 | - 语言:
- Python
- 星标数:
- 606
- 分叉数:
- 95
- 简介:
- Framework that enables fine-tuning of vision-language grounding models on custom datasets
|
|---|
| microsoft/CvT | 16,207 | - 语言:
- Python
- 星标数:
- 606
- 分叉数:
- 130
- 简介:
- This is an official implementation of CvT: Introducing Convolutions to Vision Transformers.
|
|---|
关键参数与规格
关键参数与规格| 参数 | 值 |
|---|
| 语言 | Python |
|---|
| 类别 | Model Development |
|---|
| 子类别 | Reinforcement Learning |
|---|
| 关键词 | Computer vision, RL |
|---|
| 星标数 | 607 |
|---|
| 分叉数 | 92 |
|---|
| 贡献者 | 4 |
|---|
| 创建日期 | 2020-02-09 |
|---|
| 更新日期 | 2026-09-22 |
|---|
| 1 天星标数 | 0 |
|---|
| 7 天星标数 | 0 |
|---|
| 排名 | 16,186 |
|---|
| 上次排名 | 15,973 |
|---|
| 排名变化 | -213 |
|---|
| 7 天星标排名 | 15,389 |
|---|
| 上次 7 天星标排名 | 15,397 |
|---|
| 7 天星标排名变化 | 8 |
|---|
| 总星标排名 | 16,640 |
|---|
| 上次总星标排名 | 16,613 |
|---|
| 总星标排名变化 | -27 |
|---|
| 国家 | USA |
|---|
README 摘录
CURL: Contrastive Unsupervised Representation Learning for Sample-Efficient Reinforcement Learning This repository is the official implementation of CURL for the DeepMind control experiments. Atari experiments were done in a separate codebase available here. Our implementation of SAC is based on SAC+AE by Denis Yarats. Installation All of the dependencies are in the file. They can be installed manually or with the following command: Instructions To train a CURL agent on the task from image-based observations run from the
root of this directory. The file contains the following command, which you can modify to try different environments / hyperparamters. In your console, you should see printouts that look like: For reference, the maximum score for cartpole swing up is around 845 pts, so CURL has converged to the optimal score. This takes about an hour of training depending on your GPU. Log abbreviation mapping: All data related to the run is stored in the specified . To enable model or video
saving, use the or flags. To visualize progress with tensorboard run: and go to in your browser. If you're running headlessly, try port forwarding with ssh. For GPU accelerated rendering, make sure EGL is installed on your machine and set . For environment troubleshooting issues, see the DeepMind control documentation.
常见问题
记录了多少星标和分叉？
MishaLaskin/curl 有 607 个星标和 92 个分叉。
仓库排名是多少？
MishaLaskin/curl 排名第 16,186。
记录的语言和类别是什么？
MishaLaskin/curl 有 607 个星标，语言为 Python，类别为 Model Development。
哪个仓库排名最接近？
MishaLaskin/curl 与 theAIGuysCode/yolov4-custom-functions 比较，后者排名第 16,182，有 608 个星标。
CURL: Contrastive Unsupervised Representation Learning for Sample-Efficient Reinforcement Learning
This repository is the official implementation of CURL for the DeepMind control experiments. Atari experiments were done in a separate codebase available here. Our implementation of SAC is based on SAC+AE by Denis Yarats.
Installation
All of the dependencies are in the conda_env.yml file. They can be installed manually or with the following command:
conda env create -f conda_env.yml
Instructions
To train a CURL agent on the cartpole swingup task from image-based observations run bash script/run.sh from the root of this directory. The run.sh file contains the following command, which you can modify to try different environments / hyperparamters.
CUDA_VISIBLE_DEVICES=0 python train.py \
--domain_name cartpole \
--task_name swingup \
--encoder_type pixel \
--action_repeat 8 \
--save_tb --pre_transform_image_size 100 --image_size 84 \
--work_dir ./tmp \
--agent curl_sac --frame_stack 3 \
--seed -1 --critic_lr 1e-3 --actor_lr 1e-3 --eval_freq 10000 --batch_size 128 --num_train_steps 1000000
In your console, you should see printouts that look like:
| train | E: 221 | S: 28000 | D: 18.1 s | R: 785.2634 | BR: 3.8815 | A_LOSS: -305.7328 | CR_LOSS: 190.9854 | CU_LOSS: 0.0000
| train | E: 225 | S: 28500 | D: 18.6 s | R: 832.4937 | BR: 3.9644 | A_LOSS: -308.7789 | CR_LOSS: 126.0638 | CU_LOSS: 0.0000
| train | E: 229 | S: 29000 | D: 18.8 s | R: 683.6702 | BR: 3.7384 | A_LOSS: -311.3941 | CR_LOSS: 140.2573 | CU_LOSS: 0.0000
| train | E: 233 | S: 29500 | D: 19.6 s | R: 838.0947 | BR: 3.7254 | A_LOSS: -316.9415 | CR_LOSS: 136.5304 | CU_LOSS: 0.0000
For reference, the maximum score for cartpole swing up is around 845 pts, so CURL has converged to the optimal score. This takes about an hour of training depending on your GPU.
Log abbreviation mapping:
train - training episode
E - total number of episodes
S - total number of environment steps
D - duration in seconds to train 1 episode
R - mean episode reward
BR - average reward of sampled batch
A_LOSS - average loss of actor
CR_LOSS - average loss of critic
CU_LOSS - average loss of the CURL encoder
All data related to the run is stored in the specified working_dir. To enable model or video saving, use the --save_model or --save_video flags. For all available flags, inspect train.py. To visualize progress with tensorboard run:
tensorboard --logdir log --port 6006
and go to localhost:6006 in your browser. If you're running headlessly, try port forwarding with ssh.
For GPU accelerated rendering, make sure EGL is installed on your machine and set export MUJOCO_GL=egl. For environment troubleshooting issues, see the DeepMind control documentation.