Downloads · 30 days
0
minetester-treechop_shaped-v0-train_ppo_cleanrl-seed1
rkla/minetester-treechop_shaped-v0-train_ppo_cleanrl-seed1
minetester-treechop_shaped-v0-train_ppo_cleanrl-seed1 is a reinforcement learning model from rkla. Use it for the reinforcement learning task on the model card, and read the license before you ship it in a product. It is set up for minetest-baselines.
PPO Agent Playing minetester-treechopshaped-v0
Access
Public
Updated Jul 4, 2023
Repo size
18.3 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.mp431.7 MB · 93%
At a glance
- Task
- Reinforcement Learning
- Library
- minetest-baselines
- Access
- Public
- Created
- Jul 4, 2023
- Updated
- Jul 4, 2023
- SHA
- 7e1191ac
Model card
From the Hugging Face model README
#PPO Agent Playing minetester-treechop_shaped-v0
This is a trained model of a PPO agent playing minetester-treechop_shaped-v0. The model was trained by using minetest-baselines.
Command to reproduce the training
python -m minetest_baselines.train --algo ppo --task minetester-treechop_shaped-v0 --num-envs 2 --save-model --upload-model --hf-entity rkla --total-timesteps 100 --track --wandb-entity rkla
Hyperparameters
{'anneal_lr': True,
'batch_size': 256,
'capture_video': False,
'clip_coef': 0.1,
'cuda': True,
'ent_coef': 0.01,
'env_id': 'minetester-treechop_shaped-v0',
'exp_name': 'train_ppo_cleanrl',
'gae_lambda': 0.95,
'gamma': 0.99,
'hf_entity': 'rkla',
'learning_rate': 0.00025,
'max_grad_norm': 0.5,
'minibatch_size': 64,
'norm_adv': True,
'num_envs': 2,
'num_minibatches': 4,
'num_steps': 128,
'num_updates': 0,
'save_model': True,
'seed': 1,
'target_kl': None,
'torch_deterministic': True,
'total_timesteps': 100,
'track': True,
'update_epochs': 4,
'upload_model': True,
'vf_coef': 0.5,
'wandb_entity': 'rkla',
'wandb_project_name': 'minetest-baselines'}
- Task
- Reinforcement Learning
- Library
- minetest-baselines
- Created
- Jul 4, 2023
- Updated
- Jul 4, 2023