2016-04-27 08:00:58 -07:00
import logging
import pkg_resources
import re
import sys
2016-06-12 20:56:21 -07:00
2016-04-27 08:00:58 -07:00
from gym import error
logger = logging . getLogger ( __name__ )
# This format is true today, but it's *not* an official spec.
2016-10-31 11:36:40 -07:00
# [username/](env-name)-v(version) env-name is group 1, version is group 2
#
# 2016-10-31: We're experimentally expanding the environment ID format
# to include an optional username.
2016-11-11 21:09:25 -08:00
env_id_re = re . compile ( r ' ^(?:[ \ w:-]+ \ /)?([ \ w:.-]+)-v( \ d+)$ ' )
2016-04-27 08:00:58 -07:00
def load ( name ) :
entry_point = pkg_resources . EntryPoint . parse ( ' x= {} ' . format ( name ) )
2016-04-28 17:18:27 -07:00
result = entry_point . load ( False )
return result
2016-04-27 08:00:58 -07:00
class EnvSpec ( object ) :
""" A specification for a particular instance of the environment. Used
to register the parameters for official evaluations .
Args :
id ( str ) : The official environment ID
2016-05-02 14:33:55 -04:00
entry_point ( Optional [ str ] ) : The Python entrypoint of the environment class ( e . g . module . name : Class )
2016-04-27 08:00:58 -07:00
trials ( int ) : The number of trials to average reward over
reward_threshold ( Optional [ int ] ) : The reward threshold before the task is considered solved
2016-05-31 00:25:50 -07:00
local_only : True iff the environment is to be used only on the local machine ( e . g . debugging envs )
2016-04-27 08:00:58 -07:00
kwargs ( dict ) : The kwargs to pass to the environment class
2016-05-29 09:07:09 -07:00
nondeterministic ( bool ) : Whether this environment is non - deterministic even after seeding
2016-09-27 22:59:39 -07:00
tags ( dict [ str : any ] ) : A set of arbitrary key - value tags on this environment , including simple property = True tags
2016-04-27 08:00:58 -07:00
Attributes :
id ( str ) : The official environment ID
trials ( int ) : The number of trials run in official evaluation
"""
2016-12-27 12:56:56 -08:00
def __init__ ( self , id , entry_point = None , trials = 100 , reward_threshold = None , local_only = False , kwargs = None , nondeterministic = False , tags = None ) :
2016-04-27 08:00:58 -07:00
self . id = id
# Evaluation parameters
self . trials = trials
self . reward_threshold = reward_threshold
2016-05-29 09:34:36 -07:00
# Environment properties
self . nondeterministic = nondeterministic
2016-10-31 11:36:40 -07:00
2016-09-27 23:13:11 -07:00
if tags is None :
2016-09-28 10:24:44 -07:00
tags = { }
self . tags = tags
2016-04-27 08:00:58 -07:00
# We may make some of these other parameters public if they're
# useful.
match = env_id_re . search ( id )
if not match :
raise error . Error ( ' Attempted to register malformed environment ID: {} . (Currently all IDs must be of the form {} .) ' . format ( id , env_id_re . pattern ) )
2016-05-18 12:08:27 -07:00
self . _env_name = match . group ( 1 )
2016-04-27 08:00:58 -07:00
self . _entry_point = entry_point
2016-05-31 00:25:50 -07:00
self . _local_only = local_only
2016-04-27 08:00:58 -07:00
self . _kwargs = { } if kwargs is None else kwargs
def make ( self ) :
""" Instantiates an instance of the environment with appropriate kwargs """
2016-05-06 22:26:40 -07:00
if self . _entry_point is None :
raise error . Error ( ' Attempting to make deprecated env {} . (HINT: is there a newer registered version of this env?) ' . format ( self . id ) )
2016-04-27 08:00:58 -07:00
cls = load ( self . _entry_point )
2016-04-28 17:18:27 -07:00
env = cls ( * * self . _kwargs )
2016-04-27 08:00:58 -07:00
# Make the enviroment aware of which spec it came from.
env . spec = self
return env
def __repr__ ( self ) :
return " EnvSpec( {} ) " . format ( self . id )
2016-12-28 15:16:42 -08:00
@property
def timestep_limit ( self ) :
logger . warn ( " DEPRECATION WARNING: env.spec.timestep_limit has been deprecated. Replace your call to `env.spec.timestep_limit` with `env.spec.tags.get( ' wrapper_config.TimeLimit.max_episode_steps ' )`. This change was made 12/28/2016 and is included in version 0.7.0 " )
return self . tags . get ( ' wrapper_config.TimeLimit.max_episode_steps ' )
2016-04-27 08:00:58 -07:00
class EnvRegistry ( object ) :
""" Register an env by ID. IDs remain stable over time and are
guaranteed to resolve to the same environment dynamics ( or be
desupported ) . The goal is that results on a particular environment
should always be comparable , and not depend on the version of the
code that was running .
"""
def __init__ ( self ) :
self . env_specs = { }
def make ( self , id ) :
logger . info ( ' Making new env: %s ' , id )
spec = self . spec ( id )
return spec . make ( )
def all ( self ) :
return self . env_specs . values ( )
def spec ( self , id ) :
match = env_id_re . search ( id )
if not match :
raise error . Error ( ' Attempted to look up malformed environment ID: {} . (Currently all IDs must be of the form {} .) ' . format ( id . encode ( ' utf-8 ' ) , env_id_re . pattern ) )
try :
return self . env_specs [ id ]
except KeyError :
2016-05-18 02:23:43 -07:00
# Parse the env name and check to see if it matches the non-version
# part of a valid env (could also check the exact number here)
env_name = match . group ( 1 )
2016-05-18 12:08:27 -07:00
matching_envs = [ valid_env_name for valid_env_name , valid_env_spec in self . env_specs . items ( )
if env_name == valid_env_spec . _env_name ]
2016-05-18 02:23:43 -07:00
if matching_envs :
raise error . DeprecatedEnv ( ' Env {} not found (valid versions include {} ) ' . format ( id , matching_envs ) )
else :
raise error . UnregisteredEnv ( ' No registered env with id: {} ' . format ( id ) )
2016-04-27 08:00:58 -07:00
2016-05-02 14:33:55 -04:00
def register ( self , id , * * kwargs ) :
2016-04-27 08:00:58 -07:00
if id in self . env_specs :
raise error . Error ( ' Cannot re-register id: {} ' . format ( id ) )
2016-05-02 14:33:55 -04:00
self . env_specs [ id ] = EnvSpec ( id , * * kwargs )
2016-04-27 08:00:58 -07:00
# Have a global registry
registry = EnvRegistry ( )
2016-08-20 16:05:50 -07:00
def register ( id , * * kwargs ) :
return registry . register ( id , * * kwargs )
def make ( id ) :
return registry . make ( id )
def spec ( id ) :
return registry . spec ( id )