Edit model card

PPO Agent playing BreakoutNoFrameskip-v4

This is a trained model of a PPO agent playing BreakoutNoFrameskip-v4 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

Install the RL Zoo (with SB3 and SB3-Contrib):

pip install rl_zoo3
# Download model and save it into the logs/ folder
python -m rl_zoo3.load_from_hub --algo ppo --env BreakoutNoFrameskip-v4 -orga MattStammers -f logs/
python -m rl_zoo3.enjoy --algo ppo --env BreakoutNoFrameskip-v4  -f logs/

If you installed the RL Zoo3 via pip (pip install rl_zoo3), from anywhere you can do:

python -m rl_zoo3.load_from_hub --algo ppo --env BreakoutNoFrameskip-v4 -orga MattStammers -f logs/
python -m rl_zoo3.enjoy --algo ppo --env BreakoutNoFrameskip-v4  -f logs/

Training (with the RL Zoo)

python -m rl_zoo3.train --algo ppo --env BreakoutNoFrameskip-v4 -f logs/
# Upload the model and generate video (when possible)
python -m rl_zoo3.push_to_hub --algo ppo --env BreakoutNoFrameskip-v4 -f logs/ -orga MattStammers

Hyperparameters

OrderedDict([('batch_size', 256),
             ('clip_range', 'lin_0.1'),
             ('ent_coef', 0.01),
             ('env_wrapper',
              ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
             ('frame_stack', 4),
             ('learning_rate', 'lin_2.5e-4'),
             ('n_envs', 8),
             ('n_epochs', 4),
             ('n_steps', 128),
             ('n_timesteps', 100000000.0),
             ('normalize', False),
             ('policy', 'CnnPolicy'),
             ('vf_coef', 0.5)])

Environment Arguments

{'render_mode': 'rgb_array'}
Downloads last month
0
Video Preview
loading

Evaluation results

  • mean_reward on BreakoutNoFrameskip-v4
    self-reported
    488.40 +/- 209.36