From e0e7f15da1b024131175b95d08b202f00e641ddd Mon Sep 17 00:00:00 2001 From: Varuna Jayasiri Date: Sat, 27 Mar 2021 11:54:32 +0530 Subject: [PATCH] =?UTF-8?q?=F0=9F=93=87=20version?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- docs/rl/ppo/index.html | 16 ++++++++-------- docs/rl/ppo/readme.html | 10 +++++----- labml_nn/rl/ppo/__init__.py | 6 +++--- labml_nn/rl/ppo/readme.md | 2 +- setup.py | 4 ++-- 5 files changed, 19 insertions(+), 19 deletions(-) diff --git a/docs/rl/ppo/index.html b/docs/rl/ppo/index.html index 19aaf7c2..605ea8be 100644 --- a/docs/rl/ppo/index.html +++ b/docs/rl/ppo/index.html @@ -3,24 +3,24 @@ - + - - + + - + - - + + - Proximal Policy Optimization (PPO) + Proximal Policy Optimization - PPO @@ -72,7 +72,7 @@
#
-

Proximal Policy Optimization (PPO)

+

Proximal Policy Optimization - PPO

This is a PyTorch implementation of Proximal Policy Optimization - PPO.

PPO is a policy gradient method for reinforcement learning. diff --git a/docs/rl/ppo/readme.html b/docs/rl/ppo/readme.html index a987a76c..7e257022 100644 --- a/docs/rl/ppo/readme.html +++ b/docs/rl/ppo/readme.html @@ -7,20 +7,20 @@ - + - + - + - Proximal Policy Optimization (PPO) + Proximal Policy Optimization - PPO @@ -72,7 +72,7 @@

#
-

Proximal Policy Optimization (PPO)

+

Proximal Policy Optimization - PPO

This is a PyTorch implementation of Proximal Policy Optimization - PPO.

PPO is a policy gradient method for reinforcement learning. diff --git a/labml_nn/rl/ppo/__init__.py b/labml_nn/rl/ppo/__init__.py index 1388eb68..c8bd5902 100644 --- a/labml_nn/rl/ppo/__init__.py +++ b/labml_nn/rl/ppo/__init__.py @@ -1,11 +1,11 @@ """ --- -title: Proximal Policy Optimization (PPO) +title: Proximal Policy Optimization - PPO summary: > - An annotated implementation of Proximal Policy Optimization (PPO) algorithm in PyTorch. + An annotated implementation of Proximal Policy Optimization - PPO algorithm in PyTorch. --- -# Proximal Policy Optimization (PPO) +# Proximal Policy Optimization - PPO This is a [PyTorch](https://pytorch.org) implementation of [Proximal Policy Optimization - PPO](https://arxiv.org/abs/1707.06347). diff --git a/labml_nn/rl/ppo/readme.md b/labml_nn/rl/ppo/readme.md index 37e43724..5ec04889 100644 --- a/labml_nn/rl/ppo/readme.md +++ b/labml_nn/rl/ppo/readme.md @@ -1,4 +1,4 @@ -# [Proximal Policy Optimization (PPO)](https://nn.labml.ai/rl/ppo/index.html) +# [Proximal Policy Optimization - PPO](https://nn.labml.ai/rl/ppo/index.html) This is a [PyTorch](https://pytorch.org) implementation of [Proximal Policy Optimization - PPO](https://arxiv.org/abs/1707.06347). diff --git a/setup.py b/setup.py index 7b36e4e1..05f66d01 100644 --- a/setup.py +++ b/setup.py @@ -5,7 +5,7 @@ with open("readme.md", "r") as f: setuptools.setup( name='labml-nn', - version='0.4.91', + version='0.4.93', author="Varuna Jayasiri, Nipun Wijerathne", author_email="vpjayasiri@gmail.com, hnipun@gmail.com", description="A collection of PyTorch implementations of neural network architectures and layers.", @@ -20,7 +20,7 @@ setuptools.setup( 'labml_helpers', 'labml_helpers.*', 'test', 'test.*')), - install_requires=['labml>=0.4.103', + install_requires=['labml>=0.4.109', 'labml-helpers>=0.4.76', 'torch', 'einops',