search

kh-kim / stock_market_reinforcement_learning

This project provides a stock market environment using OpenGym with Deep Q-learning and Policy Gradient.
785 stars 323 forks source link

ResourceExhaustedError #3

Open diggerdata opened 6 years ago

diggerdata commented 6 years ago

Hello,

I'm getting the following error when trying to run python market_dqn.py kospi_10.csv pg.h5

Error ResourceExhaustedError (see above for traceback): OOM when allocating tensor with shape[245760,4096]

JKyang09 commented 6 years ago

I also have the problem ResourceExhaustedError , and the problem fiexed when I change the network to a smaller one

akblissweb commented 6 years ago

I'm getting this error too. Can you explain how you made the network smaller ??