From 3c468ff5582f1c05374f674331fe8ff8e7cfc70d Mon Sep 17 00:00:00 2001 From: Bryan Collazo Date: Tue, 19 Apr 2022 08:15:51 -0400 Subject: [PATCH] Update ppo documentation (remove redundant and) (#874) * Update ppo documentation (remove redundant and) PTAL, thanks! * Update changelog * Pin ale-py version Co-authored-by: Antonin Raffin --- docs/misc/changelog.rst | 3 ++- setup.py | 2 +- stable_baselines3/ppo/ppo.py | 2 +- 3 files changed, 4 insertions(+), 3 deletions(-) diff --git a/docs/misc/changelog.rst b/docs/misc/changelog.rst index 8f37265..da33766 100644 --- a/docs/misc/changelog.rst +++ b/docs/misc/changelog.rst @@ -35,6 +35,7 @@ Others: Documentation: ^^^^^^^^^^^^^^ - Added link to gym doc and gym env checker +- Fix typo in PPO doc (@bcollazo) Release 1.5.0 (2022-03-25) @@ -964,4 +965,4 @@ And all the contributors: @wkirgsn @AechPro @CUN-bjy @batu @IljaAvadiev @timokau @kachayev @cleversonahum @eleurent @ac-93 @cove9988 @theDebugger811 @hsuehch @Demetrio92 @thomasgubler @IperGiove @ScheiklP @simoninithomas @armandpl @manuel-delverme @Gautam-J @gianlucadecola @buoyancy99 @caburu @xy9485 -@Gregwar @ycheng517 @quantitative-technologies +@Gregwar @ycheng517 @quantitative-technologies @bcollazo diff --git a/setup.py b/setup.py index 3664bbc..bb53f06 100644 --- a/setup.py +++ b/setup.py @@ -116,7 +116,7 @@ setup( # For render "opencv-python", # For atari games, - "ale-py~=0.7.4", + "ale-py==0.7.4", "autorom[accept-rom-license]~=0.4.2", "pillow", # Tensorboard support diff --git a/stable_baselines3/ppo/ppo.py b/stable_baselines3/ppo/ppo.py index 0d05b4c..346cc02 100644 --- a/stable_baselines3/ppo/ppo.py +++ b/stable_baselines3/ppo/ppo.py @@ -19,7 +19,7 @@ class PPO(OnPolicyAlgorithm): Paper: https://arxiv.org/abs/1707.06347 Code: This implementation borrows code from OpenAI Spinning Up (https://github.com/openai/spinningup/) https://github.com/ikostrikov/pytorch-a2c-ppo-acktr-gail and - and Stable Baselines (PPO2 from https://github.com/hill-a/stable-baselines) + Stable Baselines (PPO2 from https://github.com/hill-a/stable-baselines) Introduction to PPO: https://spinningup.openai.com/en/latest/algorithms/ppo.html