Skip to content
GitLab
Explore
Sign in
Register
Primary navigation
Search or go to…
Project
Bipedal Walker Evo
Manage
Activity
Members
Labels
Plan
Issues
Issue boards
Milestones
Wiki
Code
Merge requests
Repository
Branches
Commits
Tags
Repository graph
Compare revisions
Snippets
Build
Pipelines
Jobs
Pipeline schedules
Artifacts
Deploy
Releases
Package registry
Container registry
Model registry
Operate
Environments
Terraform modules
Monitor
Incidents
Analyze
Value stream analytics
Contributor analytics
CI/CD analytics
Repository analytics
Model experiments
Help
Help
Support
GitLab documentation
Compare GitLab plans
Community forum
Contribute to GitLab
Provide feedback
Terms and privacy
Keyboard shortcuts
?
Snippets
Groups
Projects
Show more breadcrumbs
Philip Maas
Bipedal Walker Evo
Commits
51884555
Commit
51884555
authored
3 years ago
by
Philip Maas
Browse files
Options
Downloads
Patches
Plain Diff
Update README.md
parent
bc97e9ab
Branches
Branches containing commit
No related tags found
No related merge requests found
Changes
1
Show whitespace changes
Inline
Side-by-side
Showing
1 changed file
README.md
+15
-16
15 additions, 16 deletions
README.md
with
15 additions
and
16 deletions
README.md
+
15
−
16
View file @
51884555
...
@@ -19,13 +19,12 @@ This is because the walker tries to generate movement by trembling with it's leg
...
@@ -19,13 +19,12 @@ This is because the walker tries to generate movement by trembling with it's leg
## Hyperparameters
## Hyperparameters
| Parameter | Description | Interval |
| Parameter | Description | Interval | Our Choice |
|-------------------|-------------------------------------------------------------|-----------|
|-------------------|-------------------------------------------------------------|-----------|------------|
|
`POP_SIZE`
| Size of population. | [0;∞[ |
|
`POP_SIZE`
| Size of population. | [0;∞[ | 50 |
|
`MUTATION_FACTOR`
| Percentage of weights that will be mutated for each mutant. | [0;1] |
|
`MUTATION_FACTOR`
| Percentage of actions that will be mutated for each walker. | [0;1] | 0.2 |
|
`ACTIONS_START`
| Number of actions in the first generation. | [0;1600] |
|
`BRAIN_SIZE`
| Number of actions in the first generation. | [0;1600] | 50 |
|
`INCREASE BY`
| Incrementation of steps for each episode. | [0;∞[ |
|
`INCREASE BY`
| Incrementation of steps for each episode. |
[
0;∞[ | 5 |
|
`MAX_STEPS`
| Number of steps that are played in one episode. | [0; 1600] |
# 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.\
...
@@ -39,15 +38,15 @@ Best score until now: 292/300 in 7000 episodes \
...
@@ -39,15 +38,15 @@ Best score until now: 292/300 in 7000 episodes \
4.
The better the reward, the higher the chance to pass weights to next gen
4.
The better the reward, the higher the chance to pass weights to next gen
## Hyperparameters
## Hyperparameters
| Parameter | Description | Interval |
| Parameter | Description | Interval |
Our Choice |
|-------------------|-------------------------------------------------------------|-----------|
|-------------------|-------------------------------------------------------------|-----------|
------------|
|
`HIDDEN_LAYER`
| Size of hidden layer. | [1;∞[ |
|
`HIDDEN_LAYER`
| Size of hidden layer. | [1;∞[ |
12 |
|
`BIAS`
| Add a bias neuron to the input layer. | {0,1} |
|
`BIAS`
| Add a bias neuron to the input layer. | {0,1} |
0 |
|
`POP_SIZE`
| Size of population. | [0;∞[ |
|
`POP_SIZE`
| Size of population. | [0;∞[ |
50 |
|
`MUTATION_FACTOR`
| Percentage of weights that will be mutated for each mutant. | [0;1] |
|
`MUTATION_FACTOR`
| Percentage of weights that will be mutated for each mutant. | [0;1] |
0.1 |
|
`LEARNING_RATE`
| This is the rate of learning. | [0;1] |
|
`LEARNING_RATE`
| This is the rate of learning. | [0;1] |
0.03 |
|
`GENS`
| Number of generations. | [0;∞[ |
|
`GENS`
| Number of generations. | [0;∞[ |
2000 |
|
`MAX_STEPS`
| Number of steps that are played in one episode. | [0; 1600] |
|
`MAX_STEPS`
| Number of steps that are played in one episode. | [0; 1600] |
300 |
# Installation
# Installation
...
...
This diff is collapsed.
Click to expand it.
Preview
0%
Loading
Try again
or
attach a new file
.
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Save comment
Cancel
Please
register
or
sign in
to comment