master
Find a file
2025-02-11 21:22:23 +01:00
oho_yfinance_neural_forecasting.ipynb Created using Colab 2025-01-08 10:24:10 +01:00
oho_yfinance_neural_forecasting_v2.ipynb Created using Colab 2025-01-10 19:07:32 +01:00
Readme.md Update Readme.md 2025-02-10 17:34:27 +01:00
RL_countdown_r1zero_01.ipynb Created using Colab 2025-02-10 17:27:22 +01:00
verl_getting_started.ipynb Created using Colab 2025-02-11 21:22:23 +01:00
Yahoo_Finance_and_neural_forecasting_02.ipynb Created using Colab 2025-01-07 16:14:20 +01:00
Yahoo_Finance_and_neural_forecasting_03.ipynb Created using Colab 2025-01-07 16:31:39 +01:00

Readme

RL_countdown_r1zero

Reinforcement Learning of a countdown function . Target: R1-Zero Base Model

Hint: the file ./TinyZero/scripts/train_tiny_zero.sh --> data.train_batch_size=256
data.val_batch_size=1312 \ ! ADJUST ! Commandline handover of override doe not work .