PPO Agent playing ReacherBulletEnv-v0
This is a trained model of a PPO agent playing ReacherBulletEnv-v0 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 ppo --env ReacherBulletEnv-v0 -orga sb3 -f logs/
python enjoy.py --algo ppo --env ReacherBulletEnv-v0 -f logs/
Training (with the RL Zoo)
python train.py --algo ppo --env ReacherBulletEnv-v0 -f logs/
# Upload the model and generate video (when possible)
python -m rl_zoo3.push_to_hub --algo ppo --env ReacherBulletEnv-v0 -f logs/ -orga sb3
Hyperparameters
OrderedDict([('batch_size', 64),
('clip_range', 'lin_0.4'),
('ent_coef', 0.0),
('env_wrapper', 'sb3_contrib.common.wrappers.TimeFeatureWrapper'),
('gae_lambda', 0.9),
('gamma', 0.99),
('learning_rate', 3e-05),
('max_grad_norm', 0.5),
('n_envs', 8),
('n_epochs', 20),
('n_steps', 512),
('n_timesteps', 1000000.0),
('normalize', True),
('policy', 'MlpPolicy'),
('policy_kwargs',
'dict(log_std_init=-2.7, ortho_init=False, '
'activation_fn=nn.ReLU, net_arch=[dict(pi=[256, 256], vf=[256, '
'256])] )'),
('sde_sample_freq', 4),
('use_sde', True),
('vf_coef', 0.5),
('normalize_kwargs', {'norm_obs': True, 'norm_reward': False})])
- Downloads last month
- 0
Evaluation results
- mean_reward on ReacherBulletEnv-v0self-reported19.12 +/- 9.53