Update README.md
Browse files
README.md
CHANGED
|
@@ -4,7 +4,7 @@ tags:
|
|
| 4 |
- deep-q-network
|
| 5 |
- reinforcement-learning
|
| 6 |
- pathfinding
|
| 7 |
-
-
|
| 8 |
license: apache-2.0
|
| 9 |
datasets:
|
| 10 |
- custom
|
|
@@ -13,11 +13,11 @@ metrics:
|
|
| 13 |
- success_rate
|
| 14 |
---
|
| 15 |
|
| 16 |
-
# Deep Q-Network for
|
| 17 |
|
| 18 |
## Model Description
|
| 19 |
|
| 20 |
-
This model is a Deep Q-Network (DQN) designed to find the most efficient path through a
|
| 21 |
|
| 22 |
## Model Architecture
|
| 23 |
|
|
@@ -29,7 +29,7 @@ The model is a fully connected neural network with the following architecture:
|
|
| 29 |
## Training
|
| 30 |
|
| 31 |
The model was trained using a hybrid approach:
|
| 32 |
-
1. **A* Algorithm**: Initially, the A* algorithm was used to find the shortest path in a static environment.
|
| 33 |
2. **Reinforcement Learning**: The DQN was trained with guidance from the A* path to improve efficiency and adaptability.
|
| 34 |
|
| 35 |
### Hyperparameters
|
|
@@ -41,7 +41,7 @@ The model was trained using a hybrid approach:
|
|
| 41 |
|
| 42 |
## Usage
|
| 43 |
|
| 44 |
-
To use this model, load the saved state dictionary and initialize the DQN with the same architecture. The model can then be used to navigate a
|
| 45 |
|
| 46 |
### Example Code
|
| 47 |
|
|
@@ -112,7 +112,7 @@ If you use this model in your research, please cite it as follows:
|
|
| 112 |
author = {Christopher Jones},
|
| 113 |
title = {Deep Q-Network for Floorplan Navigation},
|
| 114 |
year = {2024},
|
| 115 |
-
howpublished = {\url{https://huggingface.co/cajcodes/dqn-
|
| 116 |
note = {Accessed: YYYY-MM-DD}
|
| 117 |
}
|
| 118 |
```
|
|
|
|
| 4 |
- deep-q-network
|
| 5 |
- reinforcement-learning
|
| 6 |
- pathfinding
|
| 7 |
+
- floorplan
|
| 8 |
license: apache-2.0
|
| 9 |
datasets:
|
| 10 |
- custom
|
|
|
|
| 13 |
- success_rate
|
| 14 |
---
|
| 15 |
|
| 16 |
+
# Deep Q-Network for Floorplan Navigation
|
| 17 |
|
| 18 |
## Model Description
|
| 19 |
|
| 20 |
+
This model is a Deep Q-Network (DQN) designed to find the most efficient path through a floorplan without hitting obstacles. The model combines traditional pathfinding algorithms with reinforcement learning for optimal performance.
|
| 21 |
|
| 22 |
## Model Architecture
|
| 23 |
|
|
|
|
| 29 |
## Training
|
| 30 |
|
| 31 |
The model was trained using a hybrid approach:
|
| 32 |
+
1. **A(*) Algorithm**: Initially, the A* algorithm was used to find the shortest path in a static environment.
|
| 33 |
2. **Reinforcement Learning**: The DQN was trained with guidance from the A* path to improve efficiency and adaptability.
|
| 34 |
|
| 35 |
### Hyperparameters
|
|
|
|
| 41 |
|
| 42 |
## Usage
|
| 43 |
|
| 44 |
+
To use this model, load the saved state dictionary and initialize the DQN with the same architecture. The model can then be used to navigate a floorplan and find the most efficient path to the target.
|
| 45 |
|
| 46 |
### Example Code
|
| 47 |
|
|
|
|
| 112 |
author = {Christopher Jones},
|
| 113 |
title = {Deep Q-Network for Floorplan Navigation},
|
| 114 |
year = {2024},
|
| 115 |
+
howpublished = {\url{https://huggingface.co/cajcodes/dqn-floorplan-finder}},
|
| 116 |
note = {Accessed: YYYY-MM-DD}
|
| 117 |
}
|
| 118 |
```
|