Tensorflow-2-Reinforcement-Learning-Cookbook

Tensorflow-2-Reinforcement-Learning-Cookbook copied to clipboard

In Chapter 2 Notebook 7_poliucy_gradients When I increase the number of episodes to 1000 the reward never increases from -199.0

domokane

There is a bug in the way log_prob is calculated. Last step reduce_sum is supposed to be over the action space, not actions from the batch. Fixed with adding axis=1

troybvo

sac_agent render error

1

@praveen-palanisamy I am unable to create render from trading_utils.py, not creating any charts in crypto_trading_continuous_env, neither in sac_agent. Using the same code given in the source directory. Please help

rajni1624

Where is the hidden state in the DRQN code?

1

Hello! First of all, I want to commend your code, it's excellent! Thank you very much for your work! However, I have a question regarding the file Chapter03/4_drqn.py. Shouldn't it...

evbtst