How to render the environment?

[CristianMonea]

How can you render the environment using the Tensorforce library? I've tried calling environment.render, but it says that the function does not exist. This is my code:

from tensorforce.agents import Agent
from tensorforce.environments import Environment
from tensorforce.execution import Runner

# Create an OpenAI-Gym environment
environment = Environment.create(environment='gym', level='MountainCarContinuous-v0')

agent = Agent.create(agent='random', environment=environment)   

# runner = Runner(agent=agent, environment=environment) # Initialize the runner
# runner.run(num_episodes=NUM_EPISODES) # Start the runner
# runner.close()

# Train
for ep in range(NUM_EPISODES): # Number of episodes

    print('********Episode ' + str(ep) + '********')

    # Initialize episode
    states = environment.reset()
    done = False
    step = 0

    while not done: # Episode timestep
        actions = agent.act(states=states)
        states, done, reward = environment.execute(actions=actions)
        agent.observe(terminal=done, reward=reward)
        environment.render() # Gives error

environment.close()
agent.close()

[AlexKuhnle]

Hi, I haven't been checking render for a long time, I have to admit... Will have a look.

[AlexKuhnle]

Quick look: There is actually no render() function for Tensorforce environments. However, there is the visualize argument which should call it as part of execute(). Could you try whether that works?

[CristianMonea]

I've tried it, but I get the following error:

Traceback (most recent call last):

  File "c:\users\user\reinforcement learning\rl.py", line 188, in <module>
    states, done, reward = environment.execute(actions=actions, visualize=True)

TypeError: execute() got an unexpected keyword argument 'visualize'

[AlexKuhnle]

Sorry, should have been clearer: It's the environment which takes the visualize argument, so environment = Environment.create(environment='gym', level='MountainCarContinuous-v0', visualize=True).

[CristianMonea]

It works. Thank you!

[AlexKuhnle]

Great, and good to know -- as I've said, hadn't used that myself for a while. Closing then.