Downloads · 30 days
0
minetester-treechop_shaped-v0-train_dqn_cleanrl-seed1
rkla/minetester-treechop_shaped-v0-train_dqn_cleanrl-seed1
minetester-treechop_shaped-v0-train_dqn_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 cleanrl.
DQN Agent Playing minetester-treechopshaped-v0
Access
Public
Updated Jul 4, 2023
Repo size
20.9 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.mp436.8 MB · 94%
At a glance
- Task
- Reinforcement Learning
- Library
- cleanrl
- Access
- Public
- Created
- Jul 4, 2023
- Updated
- Jul 4, 2023
- SHA
- 4613c5f4
Model card
From the Hugging Face model README
#DQN Agent Playing minetester-treechop_shaped-v0
This is a trained model of a DQN 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 DQN --task minetester-treechop_shaped-v0--algo dqn --task minetester-treechop_shaped-v0 --num-envs 1 --save-model --upload-model --hf-entity rkla --buffer-size 10 --total-timesteps 100 --track --wandb-entity rkla
Hyperparameters
{'batch_size': 128,
'buffer_size': 10,
'capture_video': False,
'end_e': 0.01,
'env_id': 'minetester-treechop_shaped-v0',
'exp_name': 'train_dqn_cleanrl',
'exploration_fraction': 0.9,
'gamma': 0.99,
'hf_entity': 'rkla',
'learning_rate': 0.00025,
'learning_starts': 5000,
'num_envs': 1,
'save_model': True,
'seed': 1,
'start_e': 1,
'target_network_frequency': 10000,
'tau': 1.0,
'total_timesteps': 100,
'track': True,
'train_frequency': 10,
'upload_model': True,
'wandb_entity': 'rkla',
'wandb_project_name': 'minetest-baselines'}
- Task
- Reinforcement Learning
- Library
- cleanrl
- Created
- Jul 4, 2023
- Updated
- Jul 4, 2023