From cb4b3852d0684f5000b635294a956444b79a2776 Mon Sep 17 00:00:00 2001 From: Hongsheng Zeng Date: Sat, 21 Dec 2019 00:33:05 +0800 Subject: [PATCH] fix typo; refine readme (#190) --- .../README.md | 2 +- .../NeurIPS2019-Learn-to-Move-Challenge/README.md | 11 ++++++----- 2 files changed, 7 insertions(+), 6 deletions(-) diff --git a/examples/NeurIPS2018-AI-for-Prosthetics-Challenge/README.md b/examples/NeurIPS2018-AI-for-Prosthetics-Challenge/README.md index be7766d..dc5c8aa 100644 --- a/examples/NeurIPS2018-AI-for-Prosthetics-Challenge/README.md +++ b/examples/NeurIPS2018-AI-for-Prosthetics-Challenge/README.md @@ -37,7 +37,7 @@ For final submission, we test our model in 500 CPUs, running 10 episodes per CPU - How to Run 1. Enter the sub-folder `final_submit` - 2. Download the model file from online stroage service, [Baidu Pan](https://pan.baidu.com/s/1NN1auY2eDblGzUiqR8Bfqw) or [Google Drive](https://drive.google.com/open?id=1DQHrwtXzgFbl9dE7jGOe9ZbY0G9-qfq3) + 2. Download the model file from online storage service, [Baidu Pan](https://pan.baidu.com/s/1NN1auY2eDblGzUiqR8Bfqw) or [Google Drive](https://drive.google.com/open?id=1DQHrwtXzgFbl9dE7jGOe9ZbY0G9-qfq3) 3. Unpack the file by using: `tar zxvf saved_model.tar.gz` 4. Launch the test script: diff --git a/examples/NeurIPS2019-Learn-to-Move-Challenge/README.md b/examples/NeurIPS2019-Learn-to-Move-Challenge/README.md index 83d455b..e407c2f 100644 --- a/examples/NeurIPS2019-Learn-to-Move-Challenge/README.md +++ b/examples/NeurIPS2019-Learn-to-Move-Challenge/README.md @@ -16,7 +16,7 @@ The **PARL** team gets the first place in NeurIPS reinforcement learning competi - How to Run 1. Enter the sub-folder `final_submit` - 2. Download the model file from online stroage service: [Baidu Pan](https://pan.baidu.com/s/12LIPspckCT8-Q5U1QX69Fg) (password: `b5ck`) or [Google Drive](https://drive.google.com/file/d/1jJtOcOVJ6auz3s-TyWgUJvofPXI94yxy/view?usp=sharing) + 2. Download the model file from online storage service: [Baidu Pan](https://pan.baidu.com/s/12LIPspckCT8-Q5U1QX69Fg) (password: `b5ck`) or [Google Drive](https://drive.google.com/file/d/1jJtOcOVJ6auz3s-TyWgUJvofPXI94yxy/view?usp=sharing) 3. Unpack the file: `tar zxvf saved_models.tar.gz` 4. Launch the test script: @@ -28,7 +28,7 @@ The **PARL** team gets the first place in NeurIPS reinforcement learning competi #### 1. Run as fast as possible -> run at 3.0 m/s -> walk at 2.0 m/s -> walk slowly at 1.3 m/s The curriculum learning pipeline to get a walking slowly model is the same pipeline in [our winning solution in NeurIPS 2018: AI for Prosthetics Challenge](https://github.com/PaddlePaddle/PARL/tree/develop/examples/NeurIPS2018-AI-for-Prosthetics-Challenge). You can get a walking slowly model by following the [guide](https://github.com/PaddlePaddle/PARL/tree/develop/examples/NeurIPS2018-AI-for-Prosthetics-Challenge#part2-curriculum-learning). -We also provide a pre-trained model that walk naturally at ~1.3m/s. You can download the model file (naming `low_speed_model`) from online stroage service: [Baidu Pan](https://pan.baidu.com/s/1Mi_6bD4QxLWLdyLYe2GRFw) (password: `q9vj`) or [Google Drive](https://drive.google.com/file/d/1_cz6Cg3DAT4u2a5mxk2vP9u8nDWOE7rW/view?usp=sharing). +We also provide a pre-trained model that walk naturally at ~1.3m/s. You can download the model file (naming `low_speed_model`) from online storage service: [Baidu Pan](https://pan.baidu.com/s/1Mi_6bD4QxLWLdyLYe2GRFw) (password: `q9vj`) or [Google Drive](https://drive.google.com/file/d/1_cz6Cg3DAT4u2a5mxk2vP9u8nDWOE7rW/view?usp=sharing). #### 2. difficulty=1 > We built our distributed training agent based on PARL cluster. To start a PARL cluster, we can execute the following two xparl commands: @@ -54,6 +54,7 @@ xparl start --port 8010 --cpu_num 300 Then, we can start the distributed training by running: ```bash +# NOTE: You need provide a self-trained model, or download the `low_speed_model` as mentioned above. sh scripts/train_difficulty1.sh ./low_speed_model ``` @@ -64,15 +65,15 @@ sh scripts/eval_difficulty1.sh #### 3. difficulty=2 ```bash -sh scripts/train_difficulty2.sh [DIFFICULTY=1 MODEL] +sh scripts/train_difficulty2.sh [TRAINED DIFFICULTY=1 MODEL] ``` #### 4. difficulty=3, first target ```bash -sh scripts/train_difficulty3_first_target.sh [DIFFICULTY=2 MODEL] +sh scripts/train_difficulty3_first_target.sh [TRAINED DIFFICULTY=2 MODEL] ``` #### 5. difficulty=3 ```bash -sh scripts/train_difficulty3.sh [DIFFICULTY=3 FIRST TARGET MODEL] +sh scripts/train_difficulty3.sh [TRAINED DIFFICULTY=3 FIRST TARGET MODEL] ``` -- GitLab