Skip to content
Snippets Groups Projects
Commit f7589690 authored by Philip Maas's avatar Philip Maas
Browse files

Merge remote-tracking branch 'origin/main'

parents da9f00df 9f8e3227
No related branches found
No related tags found
No related merge requests found
...@@ -28,8 +28,8 @@ This is because the walker tries to generate movement by trembling with it's leg ...@@ -28,8 +28,8 @@ This is because the walker tries to generate movement by trembling with it's leg
# Evolution Strategies # Evolution Strategies
After 1000 episodes, which is about 1h of learning, it will reach ~250 reward.\ After 1000 episodes, which is about 1h of learning, it will reach ~250 reward.\
Best score until now: 292/300 in 7000 episodes \ Best score until now: 304/300 in 7000 episodes \
![Reward](./EvolutionStrategies/Experiments/12_1_50_0.1_decaying_300/12_2_50_0.1_decaying_300.png) ![Reward](./EvolutionStrategies/Experiments/12_1_50_decaying_decaying_300/12_1_50_decaying_decaying_300.png)
## How it works ## How it works
1. Generate a randomly weighted neural net 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