decision_transformer_2

This model is a fine-tuned version of on the city_learn dataset.

Model description

state_mean = np.array([ 6.519444444444445, 3.9837962962962963, 12.5, 16.78500002964779, 16.78491901104097, 16.785196788774595, 16.7854977140824, 72.89907407407408, 72.90567129629629, 72.909375, 72.91342592592592, 207.3190972222222, 207.3190972222222, 207.18541666666667, 207.23611111111111, 201.11863425925927, 201.11863425925927, 200.80648148148148, 200.88761574074073, 0.15636648599282596, 1.0591688615113237, 0.6963716355719771, 0.29117993655536184, 0.39915770157282743, 0.27310532142960087, 0.27310532142960087, 0.27310532142960087, 0.27310532142960087])

state_std = np.array([ 3.4712575323780417, 2.001555126539623, 6.922187552431729, 3.553894201620696, 3.553811950901204, 3.5540391337133648, 3.5546125114989646, 16.542013984734275, 16.546533736927085, 16.54789739417334, 16.548964694872215, 291.88390011273555, 291.8839001127356, 291.7552778101503, 291.83391263987227, 296.4150072818235, 296.4150072818235, 296.26064904211574, 296.30532672046087, 0.03537502595557663, 0.8835211260856368, 1.0154967670063433, 0.3233198693428126, 0.9206463117416827, 0.11787932777153287, 0.11787932777153277, 0.11787932777153269, 0.11787932777153291])

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

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: 500

Training results

Framework versions

• Transformers 4.26.1
• Pytorch 1.13.1+cu116
• Datasets 2.10.0
• Tokenizers 0.13.2