[PYTHON] Reinforcement learning 7 Learning data log output

It is assumed that you have completed reinforcement learning 6.

I would like to connect to ChainerUI, but before that, I will organize the learning data. We will continue after train.py of ChainerRL created in Reinforcement Learning 6.

It is important to note that as of November 13, 2019, the following method described near the end of the chainerRL quick reference will result in an error.

import logging
import sys
gym.undo_logger_setup()  # Turn off gym's default logger settings
logging.basicConfig(level=logging.INFO, stream=sys.stdout, format='')

chainerrl.experiments.train_agent_with_evaluation(
    agent, env,
    steps=2000,           # Train the agent for 2000 steps
    eval_n_runs=10,       # 10 episodes are sampled for each evaluation
    max_episode_len=200,  # Maximum length of each episodes
    eval_interval=1000,   # Evaluate the agent after every 1000 steps
    outdir='result')      # Save everything to 'result' directory

Rewrite the full text as follows, including changes.

train_plus.py

import chainer
import chainer.functions as F
import chainer.links as L
import chainerrl
import gym
import numpy as np

env = gym.make('CartPole-v0')
print('observation space:', env.observation_space)
print('action space:', env.action_space)

obs = env.reset()
#env.render()
print('initial observation:', obs)

action = env.action_space.sample()
obs, r, done, info = env.step(action)
print('next observation:', obs)
print('reward:', r)
print('done:', done)
print('info:', info)

class QFunction(chainer.Chain):

    def __init__(self, obs_size, n_actions, n_hidden_channels=50):
        super().__init__()
        with self.init_scope():
            self.l0 = L.Linear(obs_size, n_hidden_channels)
            self.l1 = L.Linear(n_hidden_channels, n_hidden_channels)
            self.l2 = L.Linear(n_hidden_channels, n_actions)

    def __call__(self, x, test=False):
        """
        Args:
            x (ndarray or chainer.Variable): An observation
            test (bool): a flag indicating whether it is in test mode
        """
        h = F.tanh(self.l0(x))
        h = F.tanh(self.l1(h))
        return chainerrl.action_value.DiscreteActionValue(self.l2(h))

obs_size = env.observation_space.shape[0]
n_actions = env.action_space.n
q_func = QFunction(obs_size, n_actions)
# Use Adam to optimize q_func. eps=1e-2 is for stability.
optimizer = chainer.optimizers.Adam(eps=1e-2)
optimizer.setup(q_func)
# Set the discount factor that discounts future rewards.
gamma = 0.95

# Use epsilon-greedy for exploration
explorer = chainerrl.explorers.ConstantEpsilonGreedy(
    epsilon=0.3, random_action_func=env.action_space.sample)

# DQN uses Experience Replay.
# Specify a replay buffer and its capacity.
replay_buffer = chainerrl.replay_buffer.ReplayBuffer(capacity=10 ** 6)

# Since observations from CartPole-v0 is numpy.float64 while
# Chainer only accepts numpy.float32 by default, specify
# a converter as a feature extractor function phi.
phi = lambda x: x.astype(np.float32, copy=False)

# Now create an agent that will interact with the environment.
agent = chainerrl.agents.DoubleDQN(
    q_func, optimizer, replay_buffer, gamma, explorer,
    replay_start_size=500, update_interval=1,
    target_update_interval=100, phi=phi)
# Set up the logger to print info messages for understandability.
import logging
import sys
logging.basicConfig(level=logging.INFO, stream=sys.stdout, format='')

chainerrl.experiments.train_agent_with_evaluation(
    agent, env,
    steps=20000,           # Train the agent for 2000 steps
    eval_n_steps=None,       # 10 episodes are sampled for each evaluation
    eval_n_episodes=10,       # 10 episodes are sampled for each evaluation
    eval_max_episode_len=200,  # Maximum length of each episodes
    eval_interval=1000,   # Evaluate the agent after every 1000 steps
    outdir='result')      # Save everything to 'result' directory
print('Finished.')
agent.save('agent')
env.close()

This will create scores.txt in the result folder. chainerrl is published on github, and the source file there has a description.