RL-PPO-Keras

RL-PPO-Keras copied to clipboard

After trying, gym 0.26.2 does not work, I reduce the use of 0.25.2 is feasible

zt0716

Hi, yust went thru your code and found 2 little fixes: -if self.dic_agent_conf["OPTIMIZER"] is not "Adam" and RMSProp or fallback Adam are used, they didn't had an Loss defined -Entropy...

simone1999

Hi, I think this function: _shared_network_structure is not doing what we expect actually this adds different layers with different parameters each time we call it, not shared layer

aliamiri1380

Loading models doesn't work

1

Hoping that this project is not abandoned and you're willing to patch this: When trying to load a saved model using the Agent.load_model method it will throw the exception: 'keras...

ArnoDekkersLos