Edit model card

Model description

An offline decision transformer based agent for solving Rubiks Cube.

Codes

Github repos(Give a star if found useful):

Kaggle Notebook:

Training and evaluation data

Please see the kaggle notebook: https://www.kaggle.com/code/syedjarullahhisham/drl-advanced-decisiontransformer-rubikscube

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 0.001
  • train_batch_size: 256
  • eval_batch_size: 16
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 20000

Training results

Framework versions

  • Transformers 4.41.2
  • Pytorch 2.1.2
  • Datasets 2.19.2
  • Tokenizers 0.19.1
Downloads last month
7
Safetensors
Model size
869k params
Tensor type
F32
·
Video Preview
loading