jetojedno
commented
6 years ago The solution for me (example for Discretization.ipynb):
add: from IPython import display near top
change code box to: img = plt.imshow(env.render(mode='rgb_array'))
state = env.reset() score = 0 for t in range(200): action = env.action_space.sample() img.set_data(env.render(mode='rgb_array')) display.display(plt.gcf()) display.clearoutput(wait=True) state, reward, done, = env.step(action) score += reward if done: break print('Final score:', score) env.close()
The reinforcement learning discretisation notebooks crash if being run using jupyter notebooks on remote server.