Trying to visualize the Environment in evaluate()

main.py

# Copyright 2018 Tensorforce Team. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
# ==============================================================================

import os
import logging
import sys

import tensorflow as tf

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


os.environ['TF_CPP_MIN_LOG_LEVEL'] = '3'
logger = tf.get_logger()
logger.setLevel(logging.ERROR)


def train(level, dir_name,num_episodes):
    # Create an OpenAI-Gym environment
    environment = Environment.create(
        environment='gym', level=level, visualize=False)

    # Create a PPO agent
    agent = Agent.create(
        agent='ppo',
        environment=environment,
        # Automatically configured network
        network='auto',
        # Optimization
        batch_size=10,
        update_frequency=2,
        learning_rate=1e-3,
        subsampling_fraction=0.2,
        optimization_steps=5,
        # Reward estimation
        likelihood_ratio_clipping=0.2,
        discount=0.99,
        estimate_terminal=False,
        # Critic
        critic_network='auto',
        critic_optimizer=dict(
            optimizer='adam', multi_step=10, learning_rate=1e-3
        ),
        # Preprocessing
        preprocessing=None,
        # Exploration
        exploration=0.0, variable_noise=0.0,
        # Regularization
        l2_regularization=0.0, entropy_regularization=0.0,
        # TensorFlow etc
        name='agent',
        device=None,
        parallel_interactions=1,
        seed=None,
        execution=None,
        saver=None,
        summarizer=None,
        recorder=None
    )

    # Initialize the runner
    runner = Runner(agent=agent, environment=environment)

    # Start the runner
    runner.run(num_episodes=num_episodes)
    runner.close()
    modelDir = os.path.join(os.getcwd(), dir_name)
    os.makedirs(modelDir)
    agent.save(directory=modelDir)


def evaluate(level, dir_name,num_episodes):
    environment = Environment.create(
        environment='gym', level=level, visualize=True)

    modelDir = os.path.join(os.getcwd(), dir_name)
    agent = Agent.load(directory=modelDir, environment=environment)
    runner = Runner(agent=agent, environment=level)

    # Start the runner
    runner.run(num_episodes=num_episodes)
    runner.close()


if __name__ == '__main__':
    level = 'CartPole-v0'
    dir_name = f"models_{os.getpid()}"
    num_episodes = 200
    train(level, dir_name,num_episodes)
    evaluate(level, dir_name,num_episodes)