Files
baselines/baselines/bench/benchmarks.py
pzhokhov 6c44fb28fe refactor HER - phase 1 (#767)
* joshim5 changes (width and height to WarpFrame wrapper)

* match network output with action distribution via a linear layer only if necessary (#167)

* support color vs. grayscale option in WarpFrame wrapper (#166)

* support color vs. grayscale option in WarpFrame wrapper

* Support color in other wrappers

* Updated per Peters suggestions

* fixing test failures

* ppo2 with microbatches (#168)

* pass microbatch_size to the model during construction

* microbatch fixes and test (#169)

* microbatch fixes and test

* tiny cleanup

* added assertions to the test

* vpg-related fix

* Peterz joshim5 subclass ppo2 model (#170)

* microbatch fixes and test

* tiny cleanup

* added assertions to the test

* vpg-related fix

* subclassing the model to make microbatched version of model WIP

* made microbatched model a subclass of ppo2 Model

* flake8 complaint

* mpi-less ppo2 (resolving merge conflict)

* flake8 and mpi4py imports in ppo2/model.py

* more un-mpying

* merge master

* updates to the benchmark viewer code + autopep8 (#184)

* viz docs and syntactic sugar wip

* update viewer yaml to use persistent volume claims

* move plot_util to baselines.common, update links

* use 1Tb hard drive for results viewer

* small updates to benchmark vizualizer code

* autopep8

* autopep8

* any folder can be a benchmark

* massage games image a little bit

* fixed --preload option in app.py

* remove preload from run_viewer.sh

* remove pdb breakpoints

* update bench-viewer.yaml

* fixed bug (#185)

* fixed bug 

it's wrong to do the else statement, because no other nodes would start.

* changed the fix slightly

* Refactor her phase 1 (#194)

* add monitor to the rollout envs in her RUN BENCHMARKS her

* Slice -> Slide in her benchmarks RUN BENCHMARKS her

* run her benchmark for 200 epochs

* dummy commit to RUN BENCHMARKS her

* her benchmark for 500 epochs RUN BENCHMARKS her

* add num_timesteps to her benchmark to be compatible with viewer RUN BENCHMARKS her

* add num_timesteps to her benchmark to be compatible with viewer RUN BENCHMARKS her

* add num_timesteps to her benchmark to be compatible with viewer RUN BENCHMARKS her

* disable saving of policies in her benchmark RUN BENCHMARKS her

* run fetch benchmarks with ppo2 and ddpg RUN BENCHMARKS Fetch

* run fetch benchmarks with ppo2 and ddpg RUN BENCHMARKS Fetch

* launcher refactor wip

* wip

* her works on FetchReach

* her runner refactor RUN BENCHMARKS Fetch1M

* unit test for her

* fixing warnings in mpi_average in her, skip test_fetchreach if mujoco is not present

* pickle-based serialization in her

* remove extra import from subproc_vec_env.py

* investigating differences in rollout.py

* try with old rollout code RUN BENCHMARKS her

* temporarily use DummyVecEnv in cmd_util.py RUN BENCHMARKS her

* dummy commit to RUN BENCHMARKS her

* set info_values in rollout worker in her RUN BENCHMARKS her

* bug in rollout_new.py RUN BENCHMARKS her

* fixed bug in rollout_new.py RUN BENCHMARKS her

* do not use last step because vecenv calls reset and returns obs after reset RUN BENCHMARKS her

* updated buffer sizes RUN BENCHMARKS her

* fixed loading/saving via joblib

* dust off learning from demonstrations in HER, docs, refactor

* add deprecation notice on her play and plot files

* address comments by Matthias
2018-12-19 14:44:08 -08:00

166 lines
6.0 KiB
Python

import re
import os.path as osp
import os
SCRIPT_DIR = os.path.dirname(os.path.abspath(__file__))
_atari7 = ['BeamRider', 'Breakout', 'Enduro', 'Pong', 'Qbert', 'Seaquest', 'SpaceInvaders']
_atariexpl7 = ['Freeway', 'Gravitar', 'MontezumaRevenge', 'Pitfall', 'PrivateEye', 'Solaris', 'Venture']
_BENCHMARKS = []
remove_version_re = re.compile(r'-v\d+$')
def register_benchmark(benchmark):
for b in _BENCHMARKS:
if b['name'] == benchmark['name']:
raise ValueError('Benchmark with name %s already registered!' % b['name'])
# automatically add a description if it is not present
if 'tasks' in benchmark:
for t in benchmark['tasks']:
if 'desc' not in t:
t['desc'] = remove_version_re.sub('', t['env_id'])
_BENCHMARKS.append(benchmark)
def list_benchmarks():
return [b['name'] for b in _BENCHMARKS]
def get_benchmark(benchmark_name):
for b in _BENCHMARKS:
if b['name'] == benchmark_name:
return b
raise ValueError('%s not found! Known benchmarks: %s' % (benchmark_name, list_benchmarks()))
def get_task(benchmark, env_id):
"""Get a task by env_id. Return None if the benchmark doesn't have the env"""
return next(filter(lambda task: task['env_id'] == env_id, benchmark['tasks']), None)
def find_task_for_env_id_in_any_benchmark(env_id):
for bm in _BENCHMARKS:
for task in bm["tasks"]:
if task["env_id"] == env_id:
return bm, task
return None, None
_ATARI_SUFFIX = 'NoFrameskip-v4'
register_benchmark({
'name': 'Atari50M',
'description': '7 Atari games from Mnih et al. (2013), with pixel observations, 50M timesteps',
'tasks': [{'desc': _game, 'env_id': _game + _ATARI_SUFFIX, 'trials': 2, 'num_timesteps': int(50e6)} for _game in _atari7]
})
register_benchmark({
'name': 'Atari10M',
'description': '7 Atari games from Mnih et al. (2013), with pixel observations, 10M timesteps',
'tasks': [{'desc': _game, 'env_id': _game + _ATARI_SUFFIX, 'trials': 6, 'num_timesteps': int(10e6)} for _game in _atari7]
})
register_benchmark({
'name': 'Atari1Hr',
'description': '7 Atari games from Mnih et al. (2013), with pixel observations, 1 hour of walltime',
'tasks': [{'desc': _game, 'env_id': _game + _ATARI_SUFFIX, 'trials': 2, 'num_seconds': 60 * 60} for _game in _atari7]
})
register_benchmark({
'name': 'AtariExploration10M',
'description': '7 Atari games emphasizing exploration, with pixel observations, 10M timesteps',
'tasks': [{'desc': _game, 'env_id': _game + _ATARI_SUFFIX, 'trials': 2, 'num_timesteps': int(10e6)} for _game in _atariexpl7]
})
# MuJoCo
_mujocosmall = [
'InvertedDoublePendulum-v2', 'InvertedPendulum-v2',
'HalfCheetah-v2', 'Hopper-v2', 'Walker2d-v2',
'Reacher-v2', 'Swimmer-v2']
register_benchmark({
'name': 'Mujoco1M',
'description': 'Some small 2D MuJoCo tasks, run for 1M timesteps',
'tasks': [{'env_id': _envid, 'trials': 6, 'num_timesteps': int(1e6)} for _envid in _mujocosmall]
})
register_benchmark({
'name': 'MujocoWalkers',
'description': 'MuJoCo forward walkers, run for 8M, humanoid 100M',
'tasks': [
{'env_id': "Hopper-v1", 'trials': 4, 'num_timesteps': 8 * 1000000},
{'env_id': "Walker2d-v1", 'trials': 4, 'num_timesteps': 8 * 1000000},
{'env_id': "Humanoid-v1", 'trials': 4, 'num_timesteps': 100 * 1000000},
]
})
# Bullet
_bulletsmall = [
'InvertedDoublePendulum', 'InvertedPendulum', 'HalfCheetah', 'Reacher', 'Walker2D', 'Hopper', 'Ant'
]
_bulletsmall = [e + 'BulletEnv-v0' for e in _bulletsmall]
register_benchmark({
'name': 'Bullet1M',
'description': '6 mujoco-like tasks from bullet, 1M steps',
'tasks': [{'env_id': e, 'trials': 6, 'num_timesteps': int(1e6)} for e in _bulletsmall]
})
# Roboschool
register_benchmark({
'name': 'Roboschool8M',
'description': 'Small 2D tasks, up to 30 minutes to complete on 8 cores',
'tasks': [
{'env_id': "RoboschoolReacher-v1", 'trials': 4, 'num_timesteps': 2 * 1000000},
{'env_id': "RoboschoolAnt-v1", 'trials': 4, 'num_timesteps': 8 * 1000000},
{'env_id': "RoboschoolHalfCheetah-v1", 'trials': 4, 'num_timesteps': 8 * 1000000},
{'env_id': "RoboschoolHopper-v1", 'trials': 4, 'num_timesteps': 8 * 1000000},
{'env_id': "RoboschoolWalker2d-v1", 'trials': 4, 'num_timesteps': 8 * 1000000},
]
})
register_benchmark({
'name': 'RoboschoolHarder',
'description': 'Test your might!!! Up to 12 hours on 32 cores',
'tasks': [
{'env_id': "RoboschoolHumanoid-v1", 'trials': 4, 'num_timesteps': 100 * 1000000},
{'env_id': "RoboschoolHumanoidFlagrun-v1", 'trials': 4, 'num_timesteps': 200 * 1000000},
{'env_id': "RoboschoolHumanoidFlagrunHarder-v1", 'trials': 4, 'num_timesteps': 400 * 1000000},
]
})
# Other
_atari50 = [ # actually 47
'Alien', 'Amidar', 'Assault', 'Asterix', 'Asteroids',
'Atlantis', 'BankHeist', 'BattleZone', 'BeamRider', 'Bowling',
'Breakout', 'Centipede', 'ChopperCommand', 'CrazyClimber',
'DemonAttack', 'DoubleDunk', 'Enduro', 'FishingDerby', 'Freeway',
'Frostbite', 'Gopher', 'Gravitar', 'IceHockey', 'Jamesbond',
'Kangaroo', 'Krull', 'KungFuMaster', 'MontezumaRevenge', 'MsPacman',
'NameThisGame', 'Pitfall', 'Pong', 'PrivateEye', 'Qbert',
'RoadRunner', 'Robotank', 'Seaquest', 'SpaceInvaders', 'StarGunner',
'Tennis', 'TimePilot', 'Tutankham', 'UpNDown', 'Venture',
'VideoPinball', 'WizardOfWor', 'Zaxxon',
]
register_benchmark({
'name': 'Atari50_10M',
'description': '47 Atari games from Mnih et al. (2013), with pixel observations, 10M timesteps',
'tasks': [{'desc': _game, 'env_id': _game + _ATARI_SUFFIX, 'trials': 2, 'num_timesteps': int(10e6)} for _game in _atari50]
})
# HER DDPG
_fetch_tasks = ['FetchReach-v1', 'FetchPush-v1', 'FetchSlide-v1']
register_benchmark({
'name': 'Fetch1M',
'description': 'Fetch* benchmarks for 1M timesteps',
'tasks': [{'trials': 6, 'env_id': env_id, 'num_timesteps': int(1e6)} for env_id in _fetch_tasks]
})