From 6f82e9af97a199431741ff4037726617fcf762fd Mon Sep 17 00:00:00 2001 From: "S.P. Mohanty" Date: Mon, 6 Nov 2017 00:17:57 +0100 Subject: [PATCH] Version bump, and minor additions to the documentation --- README.md | 6 +++--- docs/README.md | 15 ++++++++------- setup.py | 2 +- 3 files changed, 12 insertions(+), 11 deletions(-) diff --git a/README.md b/README.md index 882441ea..9bc3e1d9 100644 --- a/README.md +++ b/README.md @@ -1,6 +1,6 @@ # NIPS2017: Learning to run -This repository contains software required for participation in the NIPS 2017 Challenge: Learning to Run. See more details about the challenge [here](https://www.crowdai.org/challenges/nips-2017-learning-to-run). **Please read about the latest changes and the logistics of the second round [here](https://github.com/stanfordnmbl/osim-rl/tree/master/docs) (last update October 14th).** +This repository contains software required for participation in the NIPS 2017 Challenge: Learning to Run. See more details about the challenge [here](https://www.crowdai.org/challenges/nips-2017-learning-to-run). **Please read about the latest changes and the logistics of the second round [here](https://github.com/stanfordnmbl/osim-rl/tree/master/docs) (last update November 6th).** In this competition, you are tasked with developing a controller to enable a physiologically-based human model to navigate a complex obstacle course as quickly as possible. You are provided with a human musculoskeletal model and a physics-based simulation environment where you can synthesize physically and physiologically accurate motion. Potential obstacles include external obstacles like steps, or a slippery floor, along with internal obstacles like muscle weakness or motor noise. You are scored based on the distance you travel through the obstacle course in a set amount of time. @@ -288,12 +288,12 @@ Please refer to the issue https://github.com/stanfordnmbl/osim-rl/issues/34. Please refer to https://github.com/stanfordnmbl/osim-rl/issues/10 -and to +and to https://github.com/stanfordnmbl/osim-rl/issues/58 **I see only python3 environment for Linux. How to install Windows environment?** -Please refer to +Please refer to https://github.com/stanfordnmbl/osim-rl/issues/29 **How to visualize observations when running simulations on the server?** diff --git a/docs/README.md b/docs/README.md index a70e6c91..ad23148b 100644 --- a/docs/README.md +++ b/docs/README.md @@ -1,15 +1,16 @@ # Round 2 of the NIPS challenge -In order to minimize overfitting, we will check your solution in the second round on an environment with the **10 obstacles** across a total of **3 simulations**. There will be a limit of total **3 submissions** per participant throughout the entire second round. +In order to minimize overfitting, we will check your solution in the second round on an environment with the **10 obstacles** across a total of **N simulations**. There will be a limit of total **3 submissions** per participant throughout the entire second round. -Only participants with the score above 15 points on the leaderboard will be invited to submit their solutions in the second round. +Only participants with the score above 15 points on the leaderboard will be invited to submit their solutions in the second round. +More details about the actual submission format are available [here](https://hub.docker.com/r/spmohanty/crowdai-nips-learning-to-run-challenge/). You can recreate the settings of the second round using: env = RunEnv(visualize=True, max_obstacles = 10) observation = env.reset(difficulty = 2) -We are excited about these last few weeks and we are looking forward to see your final models. +We are excited about these last few weeks and we are looking forward to see your final models. Winners will be selected based on leaderboard position at the end of the second round, for these prizes: @@ -24,7 +25,7 @@ Moreover, the winner will receive travel grants to: * Applied ML Days, Switzerland, January 27th-30th 2018. Please let us know about your availability at NIPS, if you are interested in giving a talk about your solution and if you are already registered, by filling out this [form](https://plantvillage.us12.list-manage.com/track/click?u=f912313fcb27b4deb61905df6&id=cb5cbf2ad2&e=d92672213d). - + Presence at NIPS is not mandatory for eligibility, but it’s highly encouraged. If you are not competing for the prizes, but you will be present at NIPS, please also fill out the form. @@ -33,7 +34,7 @@ If you are not competing for the prizes, but you will be present at NIPS, please Grader now accepts only this version. In order to switch to the new environment you need to update the `osim-rl` scripts with the following command: pip install git+https://github.com/stanfordnmbl/osim-rl.git -U - + This release includes following bugfixes * Fixed first observation (previously it wasn't showing the first obstacle correctly). ( https://github.com/stanfordnmbl/osim-rl/issues/53 ) @@ -44,12 +45,12 @@ This release includes following bugfixes After discussing the way the reward function is computed ( https://github.com/stanfordnmbl/osim-rl/issues/43 ), we decided to further update the environment. Uptill version 1.3, the reward received at every step was the total distance travelled from the starting point minus the ligament forces. As a result, the total reward was the cummulative sum of total distances over all steps (or discreet integral of position in time) minus the total sum of ligament forces. -Since, this reward is unconventional in reinforcement learning, we updated the reward function at each step to the distance increment between the two steps minus the ligament forces. As a result, the total reward is the total distance travelled minus the ligament forces. +Since, this reward is unconventional in reinforcement learning, we updated the reward function at each step to the distance increment between the two steps minus the ligament forces. As a result, the total reward is the total distance travelled minus the ligament forces. In order to switch to the new environment you need to update the `osim-rl` scripts with the following command: pip install git+https://github.com/stanfordnmbl/osim-rl.git -U - + Note that this will change the order of magnitude of the total reward from ~1000 to ~10 (now measured in meters travelled). The change does not affect the API of observations and actions. Moreover the measures are strongly correlated and a good model in the old version should perform well in the current version. # Version 1.3 diff --git a/setup.py b/setup.py index b845cd58..66e70289 100644 --- a/setup.py +++ b/setup.py @@ -7,7 +7,7 @@ # This provides the variable `__version__`. # execfile('opensim/version.py') -__version__ = "1.5" +__version__ = "1.6" setup(name='osim-rl', version=__version__,