Skip to content
Snippets Groups Projects
Commit 5d9f5de5 authored by Philip Maas's avatar Philip Maas
Browse files

Update README.md

parent f7589690
Branches
No related tags found
No related merge requests found
...@@ -6,7 +6,7 @@ This project tries to solve OpenAI's bipedal walker using three different ways: ...@@ -6,7 +6,7 @@ This project tries to solve OpenAI's bipedal walker using three different ways:
Coming soon Coming soon
# Action Mutation # Action Mutation
Will get 0 reward, which is basically learning to prevent falling on it's head. The more actions the walker can use, the worse the reward. Will get 0 reward, which is basically learning to prevent falling on it's head. The more actions the walker can use, the worse the reward.
This is because the walker tries to generate movement by trembling with it's legs. The covered distance doesn't cover the punishment for doing actions. So after 1600 moves the walker will get a reward around -60. This is because the walker tries to generate movement by trembling with it's legs. The covered distance doesn't cover the punishment for doing actions. So after 1600 moves the walker will get a reward around -60.
![Reward](./MutateActions/5_50_50_0.2.png) ![Reward](./MutateActions/5_50_50_0.2.png)
...@@ -28,7 +28,7 @@ This is because the walker tries to generate movement by trembling with it's leg ...@@ -28,7 +28,7 @@ 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: 304/300 in 7000 episodes \ ✅ Best score until now: 304/300 in under 7000 episodes \
![Reward](./EvolutionStrategies/Experiments/12_1_50_decaying_decaying_300/12_1_50_decaying_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
......
0% Loading or .
You are about to add 0 people to the discussion. Proceed with caution.
Please register or to comment