mirror of
https://github.com/saymrwulf/stable-baselines3.git
synced 2026-11-18 09:54:10 +00:00
parent
bb01253261
commit
403fff5d50
6 changed files with 19 additions and 7 deletions
|
|
@ -1,4 +1,4 @@
|
||||||
image: stablebaselines/stable-baselines3-cpu:0.6.0a7
|
image: stablebaselines/stable-baselines3-cpu:0.6.0
|
||||||
|
|
||||||
type-check:
|
type-check:
|
||||||
script:
|
script:
|
||||||
|
|
@ -15,5 +15,4 @@ doc-build:
|
||||||
|
|
||||||
lint-check:
|
lint-check:
|
||||||
script:
|
script:
|
||||||
- pip install flake8 # TODO: remove when new version on Pypi
|
|
||||||
- make lint
|
- make lint
|
||||||
|
|
|
||||||
|
|
@ -33,6 +33,7 @@ RUN \
|
||||||
cd ${CODE_DIR}/stable-baselines3 3&& \
|
cd ${CODE_DIR}/stable-baselines3 3&& \
|
||||||
pip install -e .[extra,tests,docs] && \
|
pip install -e .[extra,tests,docs] && \
|
||||||
# Use headless version for docker
|
# Use headless version for docker
|
||||||
|
pip uninstall -y opencv-python && \
|
||||||
pip install opencv-python-headless && \
|
pip install opencv-python-headless && \
|
||||||
rm -rf $HOME/.cache/pip
|
rm -rf $HOME/.cache/pip
|
||||||
|
|
||||||
|
|
|
||||||
|
|
@ -5,7 +5,6 @@
|
||||||
|
|
||||||
**WARNING: Stable Baselines3 is currently in a beta version, breaking changes may occur before 1.0 is released**
|
**WARNING: Stable Baselines3 is currently in a beta version, breaking changes may occur before 1.0 is released**
|
||||||
|
|
||||||
Note: most of the documentation of [Stable Baselines](https://github.com/hill-a/stable-baselines) should be still valid though.
|
|
||||||
|
|
||||||
# Stable Baselines3
|
# Stable Baselines3
|
||||||
|
|
||||||
|
|
@ -35,7 +34,6 @@ These algorithms will make it easier for the research community and industry to
|
||||||
| High code coverage | :heavy_check_mark: |
|
| High code coverage | :heavy_check_mark: |
|
||||||
| Type hints | :heavy_check_mark: |
|
| Type hints | :heavy_check_mark: |
|
||||||
|
|
||||||
<!-- | Tensorboard support | :heavy_check_mark: | -->
|
|
||||||
|
|
||||||
### Roadmap to V1.0
|
### Roadmap to V1.0
|
||||||
|
|
||||||
|
|
@ -45,7 +43,6 @@ Planned features:
|
||||||
- [ ] DQN (almost ready, currently in testing phase)
|
- [ ] DQN (almost ready, currently in testing phase)
|
||||||
- [ ] DDPG (you can use its successor TD3 for now)
|
- [ ] DDPG (you can use its successor TD3 for now)
|
||||||
- [ ] HER
|
- [ ] HER
|
||||||
- [ ] Support for MultiDiscrete and MultiBinary action spaces
|
|
||||||
|
|
||||||
### Planned features (v1.1+)
|
### Planned features (v1.1+)
|
||||||
|
|
||||||
|
|
|
||||||
|
|
@ -3,9 +3,11 @@
|
||||||
Changelog
|
Changelog
|
||||||
==========
|
==========
|
||||||
|
|
||||||
Pre-Release 0.6.0a11 (WIP)
|
Pre-Release 0.6.0 (2020-06-01)
|
||||||
------------------------------
|
------------------------------
|
||||||
|
|
||||||
|
**Tensorboard support, refactored logger**
|
||||||
|
|
||||||
Breaking Changes:
|
Breaking Changes:
|
||||||
^^^^^^^^^^^^^^^^^
|
^^^^^^^^^^^^^^^^^
|
||||||
- Remove State-Dependent Exploration (SDE) support for ``TD3``
|
- Remove State-Dependent Exploration (SDE) support for ``TD3``
|
||||||
|
|
@ -47,6 +49,7 @@ Others:
|
||||||
- Added ``.readthedoc.yml`` file
|
- Added ``.readthedoc.yml`` file
|
||||||
- Added ``flake8`` and ``make lint`` command
|
- Added ``flake8`` and ``make lint`` command
|
||||||
- Added Github workflow
|
- Added Github workflow
|
||||||
|
- Added warning when passing both ``train_freq`` and ``n_episodes_rollout`` to Off-Policy Algorithms
|
||||||
|
|
||||||
Documentation:
|
Documentation:
|
||||||
^^^^^^^^^^^^^^
|
^^^^^^^^^^^^^^
|
||||||
|
|
|
||||||
|
|
@ -3,6 +3,7 @@ import os
|
||||||
import io
|
import io
|
||||||
import zipfile
|
import zipfile
|
||||||
import pickle
|
import pickle
|
||||||
|
import warnings
|
||||||
from typing import Union, Type, Optional, Dict, Any, List, Tuple, Callable
|
from typing import Union, Type, Optional, Dict, Any, List, Tuple, Callable
|
||||||
from abc import ABC, abstractmethod
|
from abc import ABC, abstractmethod
|
||||||
from collections import deque
|
from collections import deque
|
||||||
|
|
@ -800,6 +801,17 @@ class OffPolicyRLModel(BaseRLModel):
|
||||||
assert isinstance(env, VecEnv), "You must pass a VecEnv"
|
assert isinstance(env, VecEnv), "You must pass a VecEnv"
|
||||||
assert env.num_envs == 1, "OffPolicyRLModel only support single environment"
|
assert env.num_envs == 1, "OffPolicyRLModel only support single environment"
|
||||||
|
|
||||||
|
if n_episodes > 0 and n_steps > 0:
|
||||||
|
# Note we are refering to the constructor arguments
|
||||||
|
# that are named `train_freq` and `n_episodes_rollout`
|
||||||
|
# but correspond to `n_steps` and `n_episodes` here
|
||||||
|
warnings.warn("You passed a positive value for `train_freq` and `n_episodes_rollout`."
|
||||||
|
"Please make sure this is intended. "
|
||||||
|
"The agent will collect data by stepping in the environment "
|
||||||
|
"until both conditions are true: "
|
||||||
|
"`number of steps in the env` >= `train_freq` and "
|
||||||
|
"`number of episodes` > `n_episodes_rollout`")
|
||||||
|
|
||||||
if self.use_sde:
|
if self.use_sde:
|
||||||
self.actor.reset_noise()
|
self.actor.reset_noise()
|
||||||
|
|
||||||
|
|
|
||||||
|
|
@ -1 +1 @@
|
||||||
0.6.0a11
|
0.6.0
|
||||||
|
|
|
||||||
Loading…
Reference in a new issue