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
# Download model and save it into the logs/ folder<br /> python -m rl_zoo3.load_from_hub --algo ppo --env BreakoutNoFrameskip-v4 -orga sb3 -f logs/<br /> python enjoy.py --algo ppo --env BreakoutNoFrameskip-v4 -f logs/<br />

Training (with the RL Zoo)

python train.py --algo ppo --env BreakoutNoFrameskip-v4 -f logs/<br /> # Upload the model and generate video (when possible)<br /> python -m rl_zoo3.push_to_hub --algo ppo --env BreakoutNoFrameskip-v4 -f logs/ -orga sb3<br />

Hyperparameters

OrderedDict([('batch_size', 256),<br /> ('clip_range', 'lin_0.1'),<br /> ('ent_coef', 0.01),<br /> ('env_wrapper',<br /> ['stable_baselines3.common.atari_wrappers.AtariWrapper']),<br /> ('frame_stack', 4),<br /> ('learning_rate', 'lin_2.5e-4'),<br /> ('n_envs', 8),<br /> ('n_epochs', 4),<br /> ('n_steps', 128),<br /> ('n_timesteps', 10000000.0),<br /> ('policy', 'CnnPolicy'),<br /> ('vf_coef', 0.5),<br /> ('normalize', False)])<br />