Decision Transformer
This model is a fine-tuned version of on the decision_transformer_gym_replay dataset.
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0001
- train_batch_size: 64
- eval_batch_size: 8
- 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: 120
Training results
As you can see the half-cheetah is ridiculously fast!
Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
Playing the Video
The video upload preview is not working yet on this. The cheetah runs off the screen at the end and is extremely fast and effective. If you download the .mp4 you can run it in your local machine
- Downloads last month
- 1
Unable to determine this model’s pipeline type. Check the
docs
.