Downloads · 30 days
0
dqn-mountain-car
shayekh/dqn-mountain-car
dqn-mountain-car is a reinforcement learning model from shayekh. Use it for the reinforcement learning task on the model card, and read the license before you ship it in a product. The card lists the license as afl-3.0.
This is a trained model of a DQN agent playing MountainCar-v0. We train a three-layer MLP as the Q-network. We store the transitions in a replay buffer. After the network converges, we stop training and validate its p…
Access
Public
Updated Mar 26, 2023
Repo size
20.4 KB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.mp431 KB · 58%
At a glance
- Task
- Reinforcement Learning
- License
- afl-3.0
- Access
- Public
- Created
- Mar 26, 2023
- Updated
- Mar 26, 2023
- SHA
- fc7a661a
Model card
From the Hugging Face model README
DQN Agent playing MountainCar-v0
This is a trained model of a DQN agent playing MountainCar-v0. We train a three-layer MLP as the Q-network. We store the transitions in a replay buffer. After the network converges, we stop training and validate its performance in comparison to a random baseline.
Parameters:
hidden_size = 64
gamma = 0.99
epsilon_decay = 0.999
buffer_size = 10000
batch_size = 64
episodes = 10000
- Task
- Reinforcement Learning
- License
- afl-3.0
- Created
- Mar 26, 2023
- Updated
- Mar 26, 2023