YAML Metadata
Warning:
empty or missing yaml metadata in repo card
(https://huggingface.co/docs/hub/model-cards#model-card-metadata)
license: apache-2.0 tags:
DQN
DQN model applied to the this discrete environments CartPole-v1
Model Description
The model was trained from the CleanRl library using the DQN algorithm on CartPole-v1
Intended Use & Limitation
The model is intended to be used for the following environments CartPole-v1 and understand the implication of Quantization on this type of model from a pretrained state
Training Procdure
Training Hyperparameters
The folloing hyperparameters were used during training:
- exp_name: functional_dqn
- seed: 0
- torch_deterministic: True
- cuda: False
- track: True
- wandb_project_name: cleanRL
- wandb_entity: compress_rl
- capture_video: False
- env_id: CartPole-v1
- total_timesteps: 500000
- learning_rate: 0.00025
- buffer_size: 10000
- gamma: 0.99
- target_network_frequency: 500
- batch_size: 128
- start_e: 1
- end_e: 0.05
- exploration_fraction: 0.5
- learning_starts: 10000
- train_frequency: 10
- optimizer: Adan
- max_grad_norm: 0.0
- weight_decay: 0.02
- opt_eps: None
- opt_betas: None
- no_prox: False
- wandb_project: cleanrl
Framework and version
Pytorch 1.12.1+cu102
gym 0.23.1 Weights and Biases 0.13.3 Hugging Face Hub 0.11.1 Python Version 3.8.16 (default, Dec 7 2022, 01:12:13) [GCC 7.5.0]
Citation