config.json

{
  "act_dim": 6,
  "action_tanh": true,
  "activation_function": "relu",
  "adv_act_dim": 6,
  "architectures": [
    "TrainableDT"
  ],
  "attn_pdrop": 0.1,
  "bos_token_id": 50256,
  "context_size": 20,
  "embd_pdrop": 0.1,
  "eos_token_id": 50256,
  "hidden_size": 128,
  "initializer_range": 0.02,
  "lambda1": 1.0,
  "lambda2": 10.0,
  "layer_norm_epsilon": 1e-05,
  "log_interval_steps": 100,
  "max_ep_len": 1001,
  "max_ep_return": 2000.0,
  "max_obs_len": 1001,
  "max_obs_return": 1666.0162529458535,
  "min_obs_return": -327.4452760369768,
  "model_type": "decision_transformer",
  "n_head": 1,
  "n_inner": null,
  "n_layer": 3,
  "n_positions": 1024,
  "pr_act_dim": 6,
  "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": 17,
  "state_mean": [
    -0.47949490638902126,
    2.9392855446868635,
    0.2599355675435394,
    -0.13339093314086728,
    0.1662935979860262,
    -0.07257338276852067,
    0.017435688300063465,
    0.003208991217454027,
    1.7938188390218883,
    0.030872478249036942,
    0.07502310908913958,
    0.324547227176298,
    -0.27233690514262826,
    -0.04487928956840291,
    -0.16896564328141353,
    0.0648626864260328,
    0.12811998530688132
  ],
  "state_std": [
    0.130504818046764,
    1.52517394990146,
    0.5243136462888118,
    0.4580009500375659,
    0.3207804699740532,
    0.6207726011744169,
    0.37194518983551855,
    0.2779030180591103,
    1.1986000369857561,
    0.8974155842189676,
    1.6281378735321663,
    8.853020115717245,
    11.611960972109499,
    8.194997861866108,
    11.215696331272747,
    10.835559173586182,
    6.144604000512429
  ],
  "torch_dtype": "float32",
  "transformers_version": "4.31.0",
  "use_cache": true,
  "vocab_size": 1,
  "warmup_steps": 1000
}