PPO Agent playing PongNoFrameskip-v4

This is a trained model of a PPO agent playing PongNoFrameskip-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.

Codes

Github repos(Give a star if found useful):

Kaggle Notebook:

https://www.kaggle.com/code/syedjarullahhisham/drl-huggingface-unit-3-optuna-cartpole-pong-br-out

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 PongNoFrameskip-v4 -orga hishamcse -f logs/
python -m rl_zoo3.enjoy --algo ppo --env PongNoFrameskip-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 PongNoFrameskip-v4 -orga hishamcse -f logs/
python -m rl_zoo3.enjoy --algo ppo --env PongNoFrameskip-v4  -f logs/

Training (with the RL Zoo)

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

Hyperparameters

OrderedDict([('batch_size', 256),
             ('clip_range', 0.4),
             ('ent_coef', 1.6077823351479547e-08),
             ('env_wrapper',
              ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
             ('frame_stack', 4),
             ('gae_lambda', 0.9342974216877361),
             ('gamma', 0.999),
             ('learning_rate', 0.009929843682975054),
             ('n_envs', 8),
             ('n_epochs', 9),
             ('n_steps', 128),
             ('n_timesteps', 5000000.0),
             ('normalize', False),
             ('policy', 'CnnPolicy'),
             ('policy_kwargs',
              'dict(net_arch=[dict(pi=[64, 64], vf=[64, '
              '64]),],activation_fn=nn.Tanh)'),
             ('vf_coef', 0.7945615838365445)])

Environment Arguments

{'render_mode': 'rgb_array'}