Skip to content
Snippets Groups Projects
Commit 687ec2f8 authored by Philip Maas's avatar Philip Maas
Browse files

Update README.md

parent 04ff5269
No related branches found
No related tags found
No related merge requests found
......@@ -27,7 +27,7 @@ Will get 0 reward, which is basically learning to prevent falling on it's head.
# Evolution Strategies
After 1000 episodes, which is about 1h of learning, it will reach ~250 reward.\
Best score until now: 292/300 in 7000 episodes \
![Reward](/repository/EvolutionStrategies/Experiments/12 1 50 0.1 decaying 300/12_2_50_0.1_decaying_300.png "Employee Data title")
![Reward](./EvolutionStrategies/Experiments/12_1_50_0.1_decaying_300/12_2_50_0.1_decaying_300.png)
## How it works
1. Generate a randomly weighted neural net
......
0% Loading or .
You are about to add 0 people to the discussion. Proceed with caution.
Please register or to comment