gryf/coach
1
0
Fork 0
mirror of https://github.com/gryf/coach.git synced 2025-12-17 19:20:19 +01:00
Code Issues Projects Releases Wiki Activity

Update README.md

Browse Source
This commit is contained in:
Itai Caspi
2018-08-26 12:09:46 +03:00
committed by GitHub
parent 9bb7bd2e9c
commit 3fd0bf4f0f
1 changed files with 8 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
README.md
View File

@@ -17,11 +17,11 @@ Training an agent to solve an environment is as easy as running:
coach -p CartPole_DQN -r coach -p CartPole_DQN -r
``` ```
<img src="img/fetch_slide.gif" alt="Fetch Slide"/> <img src="img/pendulum.gif" alt="Pendulum"/> <img src="img/starcraft.gif" width = "280" height ="200" alt="Starcraft"/> <img src="img/fetch_slide.gif" alt="Fetch Slide"/> <img src="img/pendulum.gif" alt="Pendulum"/> <img src="img/starcraft.gif" width = "281" height ="200" alt="Starcraft"/>
<br> <br>
<img src="img/doom_deathmatch.gif" alt="Doom Deathmatch"/> <img src="img/carla.gif" alt="CARLA"/> <img src="img/montezuma.gif" alt="MontezumaRevenge"/> <img src="img/doom_deathmatch.gif" alt="Doom Deathmatch"/> <img src="img/carla.gif" alt="CARLA"/> <img src="img/montezuma.gif" alt="MontezumaRevenge" width = "164" height ="200"/>
<br> <br>
<img src="img/doom_health.gif" alt="Doom Health Gathering"/><img src="img/minitaur.gif" alt="PyBullet Minitaur"/> <img src="img/ant.gif" alt="Gym Extensions Ant"/> <img src="img/doom_health.gif" alt="Doom Health Gathering"/> <img src="img/minitaur.gif" alt="PyBullet Minitaur" width = "249" height ="200"/> <img src="img/ant.gif" alt="Gym Extensions Ant"/>
<br><br> <br><br>
Blog posts from the Intel® AI website: Blog posts from the Intel® AI website:
@@ -34,6 +34,7 @@ Contacting the Coach development team is also possible through the email [coach@
- [Coach](#coach) - [Coach](#coach)
* [Overview](#overview) * [Overview](#overview)
* [Benchmarks](#benchmarks)
* [Documentation](#documentation) * [Documentation](#documentation)
* [Installation](#installation) * [Installation](#installation)
+ [Coach Installer](#coach-installer) + [Coach Installer](#coach-installer)
@@ -46,6 +47,10 @@ Contacting the Coach development team is also possible through the email [coach@
* [Citation](#citation) * [Citation](#citation)
* [Disclaimer](#disclaimer) * [Disclaimer](#disclaimer)
## Benchmarks
One of the main challenges when building a research project, or a solution based on a published algorithm, is getting a concrete and reliable baseline that reproduces the algorithm's results, as reported by its authors. To address this problem, we are releasing a set of [benchmarks](benchmarks) that shows Coach reliably reproduces many state of the art algorithm results.
## Documentation ## Documentation
Framework documentation, algorithm description and instructions on how to contribute a new agent/environment can be found [here](https://nervanasystems.github.io/coach/). Framework documentation, algorithm description and instructions on how to contribute a new agent/environment can be found [here](https://nervanasystems.github.io/coach/).
@@ -286,7 +291,6 @@ dashboard
* [Bootstrapped Deep Q Network](https://arxiv.org/abs/1602.04621) ([code](rl_coach/agents/bootstrapped_dqn_agent.py)) * [Bootstrapped Deep Q Network](https://arxiv.org/abs/1602.04621) ([code](rl_coach/agents/bootstrapped_dqn_agent.py))
* [UCB Exploration via Q-Ensembles (UCB)](https://arxiv.org/abs/1706.01502) ([code](rl_coach/exploration_policies/ucb.py)) * [UCB Exploration via Q-Ensembles (UCB)](https://arxiv.org/abs/1706.01502) ([code](rl_coach/exploration_policies/ucb.py))
## Citation ## Citation
If you used Coach for your work, please use the following citation: If you used Coach for your work, please use the following citation: