From 62883ab4bab8ad415bf962f73d9455eae1c834a6 Mon Sep 17 00:00:00 2001 From: vincentpierre Date: Thu, 23 Jan 2020 10:42:55 -0800 Subject: [PATCH] Update the basic example documentation --- docs/Learning-Environment-Examples.md | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/docs/Learning-Environment-Examples.md b/docs/Learning-Environment-Examples.md index 93ed650d1d..f259cd778b 100644 --- a/docs/Learning-Environment-Examples.md +++ b/docs/Learning-Environment-Examples.md @@ -26,6 +26,7 @@ If you would like to contribute environments, please see our * Goal: Move to the most reward state. * Agents: The environment contains one agent. * Agent Reward Function: + * -0.01 at each step * +0.1 for arriving at suboptimal state. * +1.0 for arriving at optimal state. * Behavior Parameters: @@ -34,7 +35,7 @@ If you would like to contribute environments, please see our right). * Visual Observations: None * Float Properties: None -* Benchmark Mean Reward: 0.94 +* Benchmark Mean Reward: 0.93 ## [3DBall: 3D Balance Ball](https://youtu.be/dheeCO29-EI)