james0248's picture
Upload README.md with huggingface_hub
9d1a949
|
raw
history blame
1.03 kB
---
tags:
- SpaceInvadersNoFrameskip-v4
- deep-reinforcement-learning
- reinforcement-learning
model-index:
- name: DQN
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: SpaceInvadersNoFrameskip-v4
type: SpaceInvadersNoFrameskip-v4
metrics:
- type: mean_reward
value: 668.00 +/- 216.31
name: mean_reward
verified: false
---
# **DQN** Agent Playing **SpaceInvadersNoFrameskip-v4**
This is a trained model of a **DQN** agent playing **SpaceInvadersNoFrameskip-v4**.
To learn to use this model and train yours check Unit 3 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit3/introduction
# Hyperparameters
```python
{'batch_size': 32,
'buffer_size': 200000,
'end_e': 0.01,
'exploration_fraction': 0.1,
'gamma': 0.99,
'learning_rate': 0.0001,
'learning_starts': 80000,
'start_e': 1.0,
'target_network_frequency': 1000,
'tau': 1.0,
'total_timesteps': 2500000,
'train_frequency': 4}
```