trpo-CartPole-v1 / README.md
araffin's picture
Upload README.md with huggingface_hub
9030ade
metadata
library_name: stable-baselines3
tags:
  - CartPole-v1
  - deep-reinforcement-learning
  - reinforcement-learning
  - stable-baselines3
model-index:
  - name: TRPO
    results:
      - metrics:
          - type: mean_reward
            value: 500.00 +/- 0.00
            name: mean_reward
        task:
          type: reinforcement-learning
          name: reinforcement-learning
        dataset:
          name: CartPole-v1
          type: CartPole-v1

TRPO Agent playing CartPole-v1

This is a trained model of a TRPO agent playing CartPole-v1 using the stable-baselines3 library and the RL Zoo.

The RL Zoo is a training framework for Stable Baselines3 reinforcement learning agents, with hyperparameter optimization and pre-trained agents included.

Usage (with SB3 RL Zoo)

RL Zoo: https://github.com/DLR-RM/rl-baselines3-zoo
SB3: https://github.com/DLR-RM/stable-baselines3
SB3 Contrib: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib

# Download model and save it into the logs/ folder
python -m rl_zoo3.load_from_hub --algo trpo --env CartPole-v1 -orga sb3 -f logs/
python enjoy.py --algo trpo --env CartPole-v1  -f logs/

Training (with the RL Zoo)

python train.py --algo trpo --env CartPole-v1 -f logs/
# Upload the model and generate video (when possible)
python -m rl_zoo3.push_to_hub --algo trpo --env CartPole-v1 -f logs/ -orga sb3

Hyperparameters

OrderedDict([('batch_size', 512),
             ('cg_damping', 0.001),
             ('gae_lambda', 0.98),
             ('gamma', 0.99),
             ('learning_rate', 0.001),
             ('n_critic_updates', 20),
             ('n_envs', 2),
             ('n_steps', 512),
             ('n_timesteps', 100000.0),
             ('policy', 'MlpPolicy'),
             ('normalize', False)])