Skip to content
Snippets Groups Projects
Commit 51884555 authored by Philip Maas's avatar Philip Maas
Browse files

Update README.md

parent bc97e9ab
Branches
No related tags found
No related merge requests found
...@@ -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
......
0% Loading or .
You are about to add 0 people to the discussion. Proceed with caution.
Please register or to comment