config.json

{
  "act_dim": 3,
  "action_tanh": true,
  "activation_function": "relu",
  "adv_act_dim": 3,
  "architectures": [
    "AdversarialDT"
  ],
  "attn_pdrop": 0.1,
  "bos_token_id": 50256,
  "context_size": 20,
  "embd_pdrop": 0.1,
  "eos_token_id": 50256,
  "flag": false,
  "hidden_size": 128,
  "initializer_range": 0.02,
  "lambda1": 1.0,
  "lambda2": 1.0,
  "layer_norm_epsilon": 1e-05,
  "log_interval_steps": 100,
  "max_ep_len": 1001,
  "max_ep_return": 3871,
  "max_obs_len": 1001,
  "max_obs_return": 3871,
  "min_ep_return": 0.59533596,
  "min_obs_return": 0.59533596,
  "model_type": "decision_transformer",
  "n_head": 1,
  "n_inner": null,
  "n_layer": 3,
  "n_positions": 1024,
  "pr_act_dim": 3,
  "reorder_and_upcast_attn": false,
  "resid_pdrop": 0.1,
  "returns_scale": 1000,
  "scale_attn_by_inverse_layer_idx": false,
  "scale_attn_weights": true,
  "state_dim": 11,
  "state_mean": [
    1.3020730557253715,
    0.01905273834509088,
    -0.36272519548321536,
    -0.16859799974638057,
    0.17228675185899897,
    2.02327685891425,
    -0.0710420308260705,
    0.006762484558353705,
    -0.17713754869106765,
    -0.0961514464941647,
    -0.35985818827797467
  ],
  "state_std": [
    0.16379346557371452,
    0.07725386617281715,
    0.24012479718286456,
    0.2634233346401437,
    0.5972863553534005,
    0.8950394243184985,
    1.3217031803761354,
    0.9615967803792844,
    2.0218743383261764,
    2.9563519986131226,
    6.101592085188294
  ],
  "torch_dtype": "float32",
  "total_train_steps": 10000,
  "transformers_version": "4.29.2",
  "use_cache": true,
  "vocab_size": 1,
  "warmup_steps": 1000
}