Simple Reinforcement Learning with Tensorflow: Part 3 - Model-Based RL
Arthur Juliani

great stuff, thank you so much. One thing…If I add “plt.imshow(env.render(mode=’rgb_array’))” just after the env.reset(), which I added because I thought this might be how I can see the training sessions. Anyway, with that in, training is drastically affected. Did I do it wrong or does it actually affect training?

Show your support

Clapping shows how much you appreciated Jason Wylie’s story.