<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

decision_transformer_rb_230

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

Model description

Model on rule based interactions

state_mean = np.array([ 6.5249427917620135, 3.9993135011441647, 12.49771167048055, 16.825446250727847, 16.82580094184701, 16.828741445148562, 16.828180804459944, 72.99828375286042, 73.0012585812357, 72.99359267734553, 73.00102974828376, 208.00308924485125, 208.0545766590389, 208.2866132723112, 207.94530892448512, 201.11270022883295, 201.12254004576658, 201.15926773455377, 200.98135011441647, 0.15644143459640733, 1.064985996011147, 0.6985259305737326, 0.3315403287070356, 0.40782465644916455, 0.27306979145658644, 0.27306979145658644, 0.27306979145658644, 0.27306979145658644])

state_std = np.array([ 3.4517203419362, 2.000572882797276, 6.924445762360648, 3.5581132080274425, 3.558410500805662, 3.563460666518717, 3.562742154586059, 16.491663737463313, 16.493405084016068, 16.495564654312346, 16.49694264406781, 292.5675403707197, 292.54446787504037, 292.792528944882, 292.55912445362566, 296.2258939141665, 296.2202986371211, 296.2051386297462, 296.1393568330303, 0.03533480921331586, 0.8881741764856719, 1.0167875215772866, 0.31636407888767876, 0.9523121450900819, 0.11773822184102951, 0.11773822184102949, 0.1177382218410294, 0.11773822184102911])

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: 60

Training results

Framework versions

• Transformers 4.26.1
• Pytorch 1.13.1+cu116
• Datasets 2.10.1
• Tokenizers 0.13.2