mirror of
https://github.com/saymrwulf/stable-baselines3.git
synced 2026-05-18 21:30:19 +00:00
* Created DQN template according to the paper. Next steps: - Create Policy - Complete Training - Debug * Changed Base Class * refactor save, to be consistence with overriding the excluded_save_params function. Do not try to exclude the parameters twice. * Added simple DQN policy * Finished learn and train function - missing correct loss computation * changed collect_rollouts to work with discrete space * moved discrete space collect_rollouts to dqn * basic dqn working * deleted SDE related code * added gradient clipping and moved greedy policy to policy * changed policy to implement target network and added soft update(in fact standart tau is 1 so hard update) * fixed policy setup * rebase target_update_intervall on _n_updates * adapted all tests all tests passing * Move to stable-baseline3 * Fixes for DQN * Fix tests + add CNNPolicy * Allow any optimizer for DQN * added some util functions to create a arbitrary linear schedule, fixed pickle problem with old exploration schedule * more documentation * changed buffer dtype * refactor and document * Added Sphinx Documentation Updated changelog.rst * removed custom collect_rollouts as it is no longer necessary * Implemented suggestions to clean code and documentation. * extracted some functions on tests to reduce duplicated code * added support for exploration_fraction * Fixed exploration_fraction * Added documentation * Fixed get_linear_fn -> proper progress scaling * Merged master * Added nature reference * Changed default parameters to https://www.nature.com/articles/nature14236/tables/1 * Fixed n_updates to be incremented correctly * Correct train_freq * Doc update * added special parameter for DQN in tests * different fix for test_discrete * Update docs/modules/dqn.rst Co-authored-by: Antonin RAFFIN <antonin.raffin@ensta.org> * Update docs/modules/dqn.rst Co-authored-by: Antonin RAFFIN <antonin.raffin@ensta.org> * Update docs/modules/dqn.rst Co-authored-by: Antonin RAFFIN <antonin.raffin@ensta.org> * Added RMSProp in optimizer_kwargs, as described in nature paper * Exploration fraction is inverse of 50.000.000 (total frames) / 1.000.000 (frames with linear schedule) according to nature paper * Changelog update for buffer dtype * standard exlude parameters should be always excluded to assure proper saving only if intentionally included by ``include`` parameter * slightly more iterations on test_discrete to pass the test * added param use_rms_prop instead of mutable default argument * forgot alpha * using huber loss, adam and learning rate 1e-4 * account for train_freq in update_target_network * Added memory check for both buffers * Doc updated for buffer allocation * Added psutil Requirement * Adapted test_identity.py * Fixes with new SB3 version * Fix for tensorboard name * Convert assert to warning and fix tests * Refactor off-policy algorithms * Fixes * test: remove next_obs in replay buffer * Update changelog * Fix tests and use tmp_path where possible * Fix sampling bug in buffer * Do not store next obs on episode termination * Fix replay buffer sampling * Update comment * moved epsilon from policy to model * Update predict method * Update atari wrappers to match SB2 * Minor edit in the buffers * Update changelog * Merge branch 'master' into dqn * Update DQN to new structure * Fix tests and remove hardcoded path * Fix for DQN * Disable memory efficient replay buffer by default * Fix docstring * Add tests for memory efficient buffer * Update changelog * Split collect rollout * Move target update outside `train()` for DQN * Update changelog * Update linear schedule doc * Cleanup DQN code * Minor edit * Update version and docker images Co-authored-by: Antonin RAFFIN <antonin.raffin@ensta.org>
110 lines
5.4 KiB
Python
110 lines
5.4 KiB
Python
import os
|
|
import warnings
|
|
from typing import Dict, Any, Optional, Callable, Type, Union
|
|
|
|
import gym
|
|
|
|
from stable_baselines3.common.monitor import Monitor
|
|
from stable_baselines3.common.atari_wrappers import AtariWrapper
|
|
from stable_baselines3.common.vec_env import DummyVecEnv, SubprocVecEnv
|
|
|
|
|
|
def make_vec_env(env_id: Union[str, Type[gym.Env]],
|
|
n_envs: int = 1,
|
|
seed: Optional[int] = None,
|
|
start_index: int = 0,
|
|
monitor_dir: Optional[str] = None,
|
|
wrapper_class: Optional[Callable] = None,
|
|
env_kwargs: Optional[Dict[str, Any]] = None,
|
|
vec_env_cls: Optional[Union[DummyVecEnv, SubprocVecEnv]] = None,
|
|
vec_env_kwargs: Optional[Dict[str, Any]] = None):
|
|
"""
|
|
Create a wrapped, monitored ``VecEnv``.
|
|
By default it uses a ``DummyVecEnv`` which is usually faster
|
|
than a ``SubprocVecEnv``.
|
|
|
|
:param env_id: (str or Type[gym.Env]) the environment ID or the environment class
|
|
:param n_envs: (int) the number of environments you wish to have in parallel
|
|
:param seed: (int) the initial seed for the random number generator
|
|
:param start_index: (int) start rank index
|
|
:param monitor_dir: (str) Path to a folder where the monitor files will be saved.
|
|
If None, no file will be written, however, the env will still be wrapped
|
|
in a Monitor wrapper to provide additional information about training.
|
|
:param wrapper_class: (gym.Wrapper or callable) Additional wrapper to use on the environment.
|
|
This can also be a function with single argument that wraps the environment in many things.
|
|
:param env_kwargs: (dict) Optional keyword argument to pass to the env constructor
|
|
:param vec_env_cls: (Type[VecEnv]) A custom ``VecEnv`` class constructor. Default: None.
|
|
:param vec_env_kwargs: (dict) Keyword arguments to pass to the ``VecEnv`` class constructor.
|
|
:return: (VecEnv) The wrapped environment
|
|
"""
|
|
env_kwargs = {} if env_kwargs is None else env_kwargs
|
|
vec_env_kwargs = {} if vec_env_kwargs is None else vec_env_kwargs
|
|
|
|
def make_env(rank):
|
|
def _init():
|
|
if isinstance(env_id, str):
|
|
env = gym.make(env_id)
|
|
if len(env_kwargs) > 0:
|
|
warnings.warn("No environment class was passed (only an env ID) so ``env_kwargs`` will be ignored")
|
|
else:
|
|
env = env_id(**env_kwargs)
|
|
if seed is not None:
|
|
env.seed(seed + rank)
|
|
env.action_space.seed(seed + rank)
|
|
# Wrap the env in a Monitor wrapper
|
|
# to have additional training information
|
|
monitor_path = os.path.join(monitor_dir, str(rank)) if monitor_dir is not None else None
|
|
# Create the monitor folder if needed
|
|
if monitor_path is not None:
|
|
os.makedirs(monitor_dir, exist_ok=True)
|
|
env = Monitor(env, filename=monitor_path)
|
|
# Optionally, wrap the environment with the provided wrapper
|
|
if wrapper_class is not None:
|
|
env = wrapper_class(env)
|
|
return env
|
|
return _init
|
|
|
|
# No custom VecEnv is passed
|
|
if vec_env_cls is None:
|
|
# Default: use a DummyVecEnv
|
|
vec_env_cls = DummyVecEnv
|
|
|
|
return vec_env_cls([make_env(i + start_index) for i in range(n_envs)], **vec_env_kwargs)
|
|
|
|
|
|
def make_atari_env(env_id: Union[str, Type[gym.Env]],
|
|
n_envs: int = 1,
|
|
seed: Optional[int] = None,
|
|
start_index: int = 0,
|
|
monitor_dir: Optional[str] = None,
|
|
wrapper_kwargs: Optional[Dict[str, Any]] = None,
|
|
env_kwargs: Optional[Dict[str, Any]] = None,
|
|
vec_env_cls: Optional[Union[DummyVecEnv, SubprocVecEnv]] = None,
|
|
vec_env_kwargs: Optional[Dict[str, Any]] = None):
|
|
"""
|
|
Create a wrapped, monitored VecEnv for Atari.
|
|
It is a wrapper around ``make_vec_env`` that includes common preprocessing for Atari games.
|
|
|
|
:param env_id: (str or Type[gym.Env]) the environment ID or the environment class
|
|
:param n_envs: (int) the number of environments you wish to have in parallel
|
|
:param seed: (int) the initial seed for the random number generator
|
|
:param start_index: (int) start rank index
|
|
:param monitor_dir: (str) Path to a folder where the monitor files will be saved.
|
|
If None, no file will be written, however, the env will still be wrapped
|
|
in a Monitor wrapper to provide additional information about training.
|
|
:param wrapper_kwargs: (Dict[str, Any]) Optional keyword argument to pass to the ``AtariWrapper``
|
|
:param env_kwargs: (Dict[str, Any]) Optional keyword argument to pass to the env constructor
|
|
:param vec_env_cls: (Type[VecEnv]) A custom ``VecEnv`` class constructor. Default: None.
|
|
:param vec_env_kwargs: (Dict[str, Any]) Keyword arguments to pass to the ``VecEnv`` class constructor.
|
|
:return: (VecEnv) The wrapped environment
|
|
"""
|
|
if wrapper_kwargs is None:
|
|
wrapper_kwargs = {}
|
|
|
|
def atari_wrapper(env: gym.Env) -> gym.Env:
|
|
env = AtariWrapper(env, **wrapper_kwargs)
|
|
return env
|
|
|
|
return make_vec_env(env_id, n_envs=n_envs, seed=seed, start_index=start_index,
|
|
monitor_dir=monitor_dir, wrapper_class=atari_wrapper,
|
|
env_kwargs=env_kwargs, vec_env_cls=vec_env_cls, vec_env_kwargs=vec_env_kwargs)
|