d = False
while not d:
_, _, d, _ = env.step(env.action_space.sample())
env.reset()
env.step(env.action_space.sample())
env.close()
# Only 1 episode should be written
results = monitoring.load_results(temp)
assert len(results['episode_lengths']) == 1, "Found {} episodes written; expecting 1".format(len(results['episode_lengths']))
register(
id='test.StepsLimitCartpole-v0',
entry_point='gym.envs.classic_control:CartPoleEnv',
max_episode_steps=2
)
def test_steps_limit_restart():
with helpers.tempdir() as temp:
env = gym.make('test.StepsLimitCartpole-v0')
env = Monitor(env, temp, video_callable=False)
env.reset()
# Episode has started
_, _, done, info = env.step(env.action_space.sample())
assert done == False
# Limit reached, now we get a done signal and the env resets itself
_, _, done, info = env.step(env.action_space.sample())
from rand_param_envs.gym.envs.registration import registry, register, make, spec
# Algorithmic
# ----------------------------------------
register(
id='Copy-v0',
entry_point='gym.envs.algorithmic:CopyEnv',
max_episode_steps=200,
reward_threshold=25.0,
)
register(
id='RepeatCopy-v0',
entry_point='gym.envs.algorithmic:RepeatCopyEnv',
max_episode_steps=200,
reward_threshold=75.0,
)
register(
id='ReversedAddition-v0',
entry_point='gym.envs.algorithmic:ReversedAdditionEnv',
kwargs={'rows' : 2},
max_episode_steps=200,
reward_threshold=25.0,
)
register(
id='ReversedAddition3-v0',
entry_point='gym.envs.algorithmic:ReversedAdditionEnv',
kwargs={'rows' : 3},
from rand_param_envs.base import MetaEnv
from rand_param_envs.gym.envs.registration import register
register(
id='Walker2DRandParams-v0',
entry_point='rand_param_envs.walker2d_rand_params:Walker2DRandParamsEnv',
)
register(
id='HopperRandParams-v0',
entry_point='rand_param_envs.hopper_rand_params:HopperRandParamsEnv',
)
register(
id='PR2Env-v0',
entry_point='rand_param_envs.pr2_env_reach:PR2Env',
)