library_name: stable-baselines3
tags:
- SeaquestNoFrameskip-v4
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: PPO
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: SeaquestNoFrameskip-v4
type: SeaquestNoFrameskip-v4
metrics:
- type: mean_reward
value: 950.00 +/- 10.00
name: mean_reward
verified: false
PPO Agent playing SeaquestNoFrameskip-v4
This is a trained model of a PPO agent playing SeaquestNoFrameskip-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 SeaquestNoFrameskip-v4 -orga MattStammers -f logs/
python -m rl_zoo3.enjoy --algo ppo --env SeaquestNoFrameskip-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 SeaquestNoFrameskip-v4 -orga MattStammers -f logs/
python -m rl_zoo3.enjoy --algo ppo --env SeaquestNoFrameskip-v4 -f logs/
Training (with the RL Zoo)
python -m rl_zoo3.train --algo ppo --env SeaquestNoFrameskip-v4 -f logs/
# Upload the model and generate video (when possible)
python -m rl_zoo3.push_to_hub --algo ppo --env SeaquestNoFrameskip-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', 10000000.0),
('normalize', False),
('policy', 'CnnPolicy'),
('vf_coef', 0.5)])
Environment Arguments
{'render_mode': 'rgb_array'}
This agent has decided that it is optimal to exist without worrying about oxygen. Seems to maximise score consistency but is probably not a globally optimal strategy.