Category "reinforcement-learning"

installing box2d gym ai

I want to train DQN on CarRacing environmnet but when I want to import it using bellow command there is an error. env = gym.make('CarRacing-v0').unwrapped Attr

A2C not converge as the loss explode

I'm experimenting with Advantage Actor Critic algorithm, and the loss explode exponentially. like iteration actor_loss critic_loss 17 -0.072878 0.003239 78 -25

Tensorflow and Multiprocessing: Passing Sessions

I have recently been working on a project that uses a neural network for virtual robot control. I used tensorflow to code it up and it runs smoothly. So far, I