def test_render_episodes_to_str(self):
ppo_agent = PpoAgent( 'CartPole-v0', training_duration=TrainingDurationSingleEpisode(), logging=LoggingVerbose() )
ppo_agent.train()
result = ppo_agent.render_episodes_to_str()
assert isinstance(result,str), "render_episodes_to_str did not return a string"
return
#
# simple easyagents demo using cartpole
from easyagents.tfagents import PpoAgent
from easyagents.config import TrainingDurationSingleEpisode
from easyagents.config import TrainingDurationFast
from easyagents.config import LoggingVerbose
ppo_agent = PpoAgent(gym_env_name='CartPole-v0',
training_duration=TrainingDurationFast(),
logging=LoggingVerbose())
ppo_agent.train()
ppo_agent.plot_average_rewards()
ppo_agent.plot_losses()
ppo_agent.render_episodes_to_mp4()
ppo_agent.render_episodes_to_html(fps=20)
def test_plot_with_ylim(self):
ppo_agent = PpoAgent( 'CartPole-v0', training_duration=TrainingDurationSingleEpisode(), logging=LoggingVerbose() )
ppo_agent.train()
ppo_agent.plot_losses(ylim=[10,20])
return
def test_render_episodes(self):
ppo_agent = PpoAgent( 'CartPole-v0', training_duration=TrainingDurationSingleEpisode(), logging=LoggingVerbose() )
ppo_agent.train()
ppo_agent.render_episodes()
return
def test_plot_no_ylim(self):
ppo_agent = PpoAgent( 'CartPole-v0', training_duration=TrainingDurationSingleEpisode(), logging=LoggingVerbose() )
ppo_agent.train()
ppo_agent.plot_average_rewards()
return
def test_ppo_str(self):
ppo_agent = PpoAgent( self.gym_env_name, training_duration=TrainingDurationFast() )
result = str(ppo_agent)
print(result)
return
def test_ppo_train(self):
ppo_agent = PpoAgent( self.gym_env_name, training_duration=TrainingDurationFast() )
ppo_agent.train()
return
def test_ppo_create(self):
ppo_agent = PpoAgent( self.gym_env_name )
self.assertIsNotNone( ppo_agent, "failed to create a tfagents.Ppo instance for " + self.gym_env_name )
return
if not 'isEnvRegistered' in locals():
env_name = "Berater-v1"
gym.envs.registration.register(id=env_name,
entry_point=BeraterEnv,
max_episode_steps=1000)
isEnvRegistered = True
print("Berater registered as '" + env_name + "'")
else:
print("Already registered")
#%%
from easyagents.tfagents import PpoAgent
from easyagents.config import TrainingDurationFast
from easyagents.config import LoggingVerbose
ppo_agent = PpoAgent(
gym_env_name='Berater-v1',
fc_layers=(500, 500, 500),
training_duration=TrainingDurationFast(max_steps_per_episode=50),
# logging=LoggingVerbose(),
learning_rate=1e-4)
ppo_agent.train()
#%%
ppo_agent.render_episodes_to_mp4(num_episodes=1,
filepath='c:\\temp\\_orso.mp4')
#%%