40 Commits

Author SHA1 Message Date
Yuge Zhang
65c4e3d4cd
Fix NNI tests upon v2.9 upgrade (#750)
* Fix NNI tests upon v2.9 upgrade

* Un-ignore

* fix
2022-09-26 13:55:26 -07:00
Markus Krimmel
ea36dc5195
Changes to support Gym 0.26.0 (#748)
* Changes to support Gym 0.26.0

* Replace map by simpler list comprehension

* Use syntax that is compatible with python 3.7

* Format code

* Fix environment seeding in test environment, fix buffer_profile test

* Remove self.seed() from __init__

* Fix random number generation

* Fix throughput tests

* Fix tests

* Removed done field from Buffer, fixed throughput test, turned off wandb, fixed formatting, fixed type hints, allow preprocessing_fn with truncated and terminated arguments, updated docstrings

* fix lint

* fix

* fix import

* fix

* fix mypy

* pytest --ignore='test/3rd_party'

* Use correct step API in _SetAttrWrapper

* Format

* Fix mypy

* Format

* Fix pydocstyle.
2022-09-26 09:31:23 -07:00
Jiayi Weng
65054847ef
bump version to 0.4.9 (#684) 2022-07-05 01:07:16 +08:00
Jiayi Weng
2a7c151738
Add vecenv wrappers for obs_norm to support running mujoco experiment with envpool (#628)
- add VectorEnvWrapper and VectorEnvNormObs
- obs_rms store in policy save/load
- align mujoco scripts with atari: obs_norm, envpool, wandb and README
2022-05-05 19:55:15 +08:00
Jose Antonio Martin H
10d919052b
Add Trainers as generators (#559)
The new proposed feature is to have trainers as generators.
The usage pattern is:

```python
trainer = OnPolicyTrainer(...)
for epoch, epoch_stat, info in trainer:
    print(f"Epoch: {epoch}")
    print(epoch_stat)
    print(info)
    do_something_with_policy()
    query_something_about_policy()
    make_a_plot_with(epoch_stat)
    display(info)
```

- epoch int: the epoch number
- epoch_stat dict: a large collection of metrics of the current epoch, including stat
- info dict: the usual dict out of the non-generator version of the trainer

You can even iterate on several different trainers at the same time:

```python
trainer1 = OnPolicyTrainer(...)
trainer2 = OnPolicyTrainer(...)
for result1, result2, ... in zip(trainer1, trainer2, ...):
    compare_results(result1, result2, ...)
```

Co-authored-by: Jiayi Weng <trinkle23897@gmail.com>
2022-03-18 00:26:14 +08:00
Jiayi Weng
c248b4f87e
fix conda support and keep API compatibility (#536)
* loose constrains

* fix nni issue (#478)

* fix coverage
2022-02-26 00:05:02 +08:00
Chengqi Duan
23fbc3b712
upgrade gym version to >=0.21, fix related CI and update examples/atari (#534)
Co-authored-by: Jiayi Weng <trinkle23897@gmail.com>
2022-02-25 07:40:33 +08:00
Jiayi Weng
3d697aa4c6
make unit test faster (#522)
* test cache expert data in offline training

* faster cql test

* faster tests

* use dummy

* test ray dependency
2022-02-09 00:24:52 +08:00
Ayush Chaurasia
22d7bf38c8
Improve W&B logger (#441)
- rename WandBLogger -> WandbLogger
- add save_data and restore_data
- allow more input arguments for wandb init
- integrate wandb into test/modelbase/test_psrl.py and examples/atari/atari_dqn.py
- documentation update
2021-09-24 21:52:23 +08:00
n+e
fc251ab0b8
bump to v0.4.3 (#432)
* add makefile
* bump version
* add isort and yapf
* update contributing.md
* update PR template
* spelling check
2021-09-03 05:05:04 +08:00
n+e
e4f4f0e144
fix docs build failure and a bug in a2c/ppo optimizer (#428)
* fix rtfd build

* list + list -> set.union

* change seed of test_qrdqn

* add py39 test
2021-08-30 02:07:03 +08:00
n+e
ebaca6f8da
add vizdoom example, bump version to 0.4.2 (#384) 2021-06-26 18:08:41 +08:00
n+e
ff4d3cd714
Support different state size and fix exception in venv.__del__ (#352)
- Batch: do not raise error when it finds list of np.array with different shape[0].

- Venv's obs: add try...except block for np.stack(obs_list)

- remove venv.__del__ since it is buggy
2021-04-25 15:23:46 +08:00
n+e
f68cb78ed7
Add self-hosted runner for GPU checks (#339) 2021-04-18 16:57:37 +08:00
n+e
825da9bc53
add cross-platform test and release 0.4.1 (#331)
* bump to 0.4.1

* add cross-platform test
2021-03-31 15:14:22 +08:00
n+e
b284ace102
type check in unit test (#200)
Fix #195: Add mypy test in .github/workflows/docs_and_lint.yml.

Also remove the out-of-the-date api
2020-09-13 19:31:50 +08:00
n+e
b86d78766b
fix docs and add docstring check (#210)
- fix broken links and out-of-the-date content
- add pydocstyle and doc8 check
- remove collector.seed and collector.render
2020-09-11 07:55:37 +08:00
ChenDRAG
996e2f7c9b
Add profile workflow (#143)
* add a workflow to profile batch
* buffer profiling
* collector profiling

Co-authored-by: Trinkle23897 <463003665@qq.com>
Co-authored-by: Huayu Chen(陈华玉) <chenhuay17@gamil.com>
2020-08-02 18:24:40 +08:00
n+e
bd9c3c7f8d
docs fix and v0.2.5 (#156)
* pre

* update docs

* update docs

* $ in bash

* size -> hidden_layer_size

* doctest

* doctest again

* filter a warning

* fix bug

* fix examples

* test fail

* test succ
2020-07-22 14:42:08 +08:00
youkaichao
affeec13de Improve Batch (#128)
* minor polish

* improve and implement Batch.cat_

* bugfix for buffer.sample with field impt_weight

* restore the usage of a.cat_(b)

* fix 2 bugs in batch and add corresponding unittest

* code fix for update

* update is_empty to recognize empty over empty; bugfix for len

* bugfix for update and add testcase

* add testcase of update

* fix docs

* fix docs

* fix docs [ci skip]

* fix docs [ci skip]

Co-authored-by: Trinkle23897 <463003665@qq.com>
2020-07-13 17:33:01 +08:00
Trinkle23897
b32b96cd3e seperate flake8 lint 2020-06-09 10:33:48 +08:00
Trinkle23897
ba1b3e54eb fix #69 2020-06-01 08:30:09 +08:00
Trinkle23897
3243484f8e show stat in pytest 2020-05-16 08:48:12 +08:00
Trinkle23897
9b26137cd2 add type annotation 2020-05-12 11:31:47 +08:00
Trinkle23897
6b96f124ae fix pdqn 2020-04-26 15:11:20 +08:00
Trinkle23897
befdfb07e8 polish docs 2020-04-11 19:29:46 +08:00
Trinkle23897
6da80e045a fix rnn (#19), add __repr__, and fix #26 2020-04-09 19:53:45 +08:00
Trinkle23897
6c8edf6a3a codecov badge 2020-04-07 11:17:10 +08:00
Trinkle23897
f68f23292e update readme and force flake8 2020-03-28 13:27:01 +08:00
Trinkle23897
044aae4355 add baseline and rlpyt result 2020-03-27 16:24:07 +08:00
Trinkle23897
d64d78d769 seed??? 2020-03-20 21:51:09 +08:00
Trinkle23897
9c5417dd51 change env to vecenv for higher code coverage rate 2020-03-18 21:56:03 +08:00
Trinkle23897
64bab0b6a0 ddpg 2020-03-18 21:45:41 +08:00
Trinkle23897
8b0b970c9b add speed stat 2020-03-16 15:04:58 +08:00
Trinkle23897
f16e05c0e7 maybe finished collector? 2020-03-13 17:49:22 +08:00
Trinkle23897
6632e47b9d add test_buffer 2020-03-11 17:28:51 +08:00
Trinkle23897
04557fdb82 env test \ ray 2020-03-11 16:14:53 +08:00
Trinkle23897
7533e5b0ac add first test 2020-03-11 10:56:38 +08:00
Trinkle23897
5550aed0a1 flake8 fix 2020-03-11 09:38:14 +08:00
Trinkle23897
776acd9f13 github ci 2020-03-11 09:18:28 +08:00