config.json

{
  "act_dim": 3,
  "action_tanh": true,
  "activation_function": "relu",
  "adv_act_dim": 3,
  "architectures": [
    "VanillaDT"
  ],
  "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": 1000,
  "max_ep_return": 3223,
  "max_obs_len": 1000,
  "max_obs_return": 3223,
  "min_ep_return": 2.7032015323638916,
  "min_obs_return": 2.7032015323638916,
  "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": [
    1.3106526835537706,
    -0.08469277108602184,
    -0.5382069126657438,
    -0.0720346361434995,
    0.04932667926114204,
    2.1067770148789027,
    -0.15017017617998743,
    0.008783139314902764,
    -0.2848213106799807,
    -0.18540193496296434,
    -0.28461201593116625
  ],
  "state_std": [
    0.17792387447055596,
    0.05445541724664148,
    0.2130354611105368,
    0.14523059124520427,
    0.6124522430667698,
    0.8519473510741823,
    1.4517896067649523,
    0.6753408994067926,
    1.5365847791743765,
    1.6180626583607793,
    5.6093664355155495
  ],
  "torch_dtype": "float32",
  "total_train_steps": 10000,
  "transformers_version": "4.31.0",
  "use_cache": true,
  "vocab_size": 1,
  "warmup_steps": 1000
}