metadata
tags:
- reinforcement-learning
- deep-reinforcement-learning
- A2C
- CartPole-v1
library_name: hellrl
model-index:
- name: A2C
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: CartPole-v1
type: CartPole-v1
metrics:
- type: mean_reward
value: 500.00 +/- 0.00
name: mean_reward
verified: false
(HellRL) A2C Agent Playing CartPole-v1
The model was trained by using hellrl.
Command to reproduce the training
curl -OL https://huggingface.co/alperenunlu/CartPole-v1-a2c/raw/main/a2c.py
curl -OL https://huggingface.co/alperenunlu/CartPole-v1-a2c/raw/main/pyproject.toml
curl -OL https://huggingface.co/alperenunlu/CartPole-v1-a2c/raw/main/uv.lock
uv run a2c.py
Hyperparameters
{'ent_coef': 0.01,
'env_id': 'CartPole-v1',
'eval_episodes': 10,
'evaluate': True,
'exp_name': 'a2c',
'gae_lambda': 0.95,
'gamma': 0.99,
'hf_entity': 'alperenunlu',
'learning_rate': 0.0003,
'log_interval': 100,
'n_envs': 32,
'num_steps': 20,
'push_model': True,
'seed': 1,
'total_timesteps': 150_000,
'video_capture_frequency': 50}