db50bca7fd
* scenarionet training * wandb * train utils * fix callback * run PPO * use pg test * save path * use torch * add dependency * update ignore * update training * large model * use curriculum training * add time to exp name * storage_path * restore * update training * use my key * add log message * check seed * restore callback * restore call bacl * add log message * add logging message * restore ray1.4 * length 500 * ray 100 * wandb * use tf * more levels * add callback * 10 worker * show level * no env horizon * callback result level * more call back * add diffuculty * add mroen stat * mroe stat * show levels * add callback * new * ep len 600 * fix setup * fix stepup * fix to 3.8 * update setup * parallel worker! * new exp * add callback * lateral dist * pg dataset * evaluate * modify config * align config * train single RL * update training script * 100w eval * less eval to reveal * 2000 env eval * new trianing * eval 1000 * update eval * more workers * more worker * 20 worker * dataset to database * split tool! * split dataset * try fix * train 003 * fix mapping * fix test * add waymo tqdm * utils * fix bug * fix bug * waymo * int type * 8 worker read * disable * read file * add log message * check existence * dist 0 * int * check num * suprass warning * add filter API * filter * store map false * new * ablation * filter * fix * update filyter * reanme to from * random select * add overlapping checj * fix * new training sceheme * new reward * add waymo train script * waymo different config * copy raw data * fix bug * add tqdm * update readme * waymo * pg * max lateral dist 3 * pg * crash_done instead of penalty * no crash done * gpu * update eval script * steering range penalty * evaluate * finish pg * update setup * fix bug * test * fix * add on line * train nuplan * generate sensor * udpate training * static obj * multi worker eval * filx bug * use ray for testing * eval! * filter senario * id filter * fox bug * dist = 2 * filter * eval * eval ret * ok * update training pg * test before use * store data=False * collect figures * capture pic --------- Co-authored-by: Quanyi Li <quanyi@bolei-gpu02.cs.ucla.edu>
39 lines
1.4 KiB
Python
39 lines
1.4 KiB
Python
"""
|
|
Procedure to use wandb:
|
|
|
|
1. Logup in wandb: https://wandb.ai/
|
|
2. Get the API key in personal setting
|
|
3. Store API key (a string)to some file as: ~/wandb_api_key_file.txt
|
|
4. Install wandb: pip install wandb
|
|
5. Fill the "wandb_key_file", "wandb_project" keys in our train function.
|
|
|
|
Note1: You don't need to specify who own "wandb_project", for example, in team "drivingforce"'s project
|
|
"representation", you only need to fill wandb_project="representation"
|
|
|
|
Note2: In wanbd, there are "team name", "project name", "group name" and "trial_name". We only need to care
|
|
"team name" and "project name". The "team name" is set to "drivingforce" by default. You can also use None to
|
|
log result to your personal domain. The "group name" of the experiment is exactly the "exp_name" in our context, like
|
|
"0304_train_ppo" or so.
|
|
|
|
Note3: It would be great to change the x-axis in wandb website to "timesteps_total".
|
|
|
|
Peng Zhenghao, 20210402
|
|
"""
|
|
from ray import tune
|
|
|
|
from scenarionet_training.train_utils.utils import train
|
|
|
|
if __name__ == "__main__":
|
|
config = dict(env="CartPole-v0", num_workers=0, lr=tune.grid_search([1e-2, 1e-4]))
|
|
train(
|
|
"PPO",
|
|
exp_name="test_wandb",
|
|
stop=10000,
|
|
config=config,
|
|
custom_callback=False,
|
|
test_mode=False,
|
|
local_mode=False,
|
|
wandb_project="TEST",
|
|
wandb_team="drivingforce" # drivingforce is set to default. Use None to log to your personal domain!
|
|
)
|