# Decision Transformer ## Overview Decision Transformer モデルは、[Decision Transformer: Reinforcement Learning via Sequence Modeling](https://huggingface.co/papers/2106.01345) で提案されました。 Lili Chen, Kevin Lu, Aravind Rajeswaran, Kimin Lee, Aditya Grover, Michael Laskin, Pieter Abbeel, Aravind Srinivas, Igor Mordatch. 論文の要約は次のとおりです。 _強化学習（RL）をシーケンスモデリング問題として抽象化するフレームワークを紹介します。 これにより、Transformer アーキテクチャのシンプルさとスケーラビリティ、および関連する進歩を活用できるようになります。 GPT-x や BERT などの言語モデリングで。特に、Decision Transformer というアーキテクチャを紹介します。 RL の問題を条件付きシーケンス モデリングとして投げかけます。値関数に適合する以前の RL アプローチとは異なり、 ポリシー勾配を計算すると、Decision Transformer は因果的にマスクされたアルゴリズムを利用して最適なアクションを出力するだけです。 変成器。望ましいリターン (報酬)、過去の状態、アクションに基づいて自己回帰モデルを条件付けすることにより、 Decision Transformer モデルは、望ましいリターンを達成する将来のアクションを生成できます。そのシンプルさにも関わらず、 Decision Transformer は、最先端のモデルフリーのオフライン RL ベースラインのパフォーマンスと同等、またはそれを超えています。 Atari、OpenAI Gym、Key-to-Door タスク_ このバージョンのモデルは、状態がベクトルであるタスク用です。 このモデルは、[edbeeching](https://huggingface.co/edbeeching) によって提供されました。元のコードは [ここ](https://github.com/kzl/decision-transformer) にあります。 ## DecisionTransformerConfig[[transformers.DecisionTransformerConfig]]
class transformers.DecisionTransformerConfigtransformers.DecisionTransformerConfighttps://github.com/huggingface/transformers/blob/v4.57.0/src/transformers/models/decision_transformer/configuration_decision_transformer.py#L24[{"name": "state_dim", "val": " = 17"}, {"name": "act_dim", "val": " = 4"}, {"name": "hidden_size", "val": " = 128"}, {"name": "max_ep_len", "val": " = 4096"}, {"name": "action_tanh", "val": " = True"}, {"name": "vocab_size", "val": " = 1"}, {"name": "n_positions", "val": " = 1024"}, {"name": "n_layer", "val": " = 3"}, {"name": "n_head", "val": " = 1"}, {"name": "n_inner", "val": " = None"}, {"name": "activation_function", "val": " = 'relu'"}, {"name": "resid_pdrop", "val": " = 0.1"}, {"name": "embd_pdrop", "val": " = 0.1"}, {"name": "attn_pdrop", "val": " = 0.1"}, {"name": "layer_norm_epsilon", "val": " = 1e-05"}, {"name": "initializer_range", "val": " = 0.02"}, {"name": "scale_attn_weights", "val": " = True"}, {"name": "use_cache", "val": " = True"}, {"name": "bos_token_id", "val": " = 50256"}, {"name": "eos_token_id", "val": " = 50256"}, {"name": "scale_attn_by_inverse_layer_idx", "val": " = False"}, {"name": "reorder_and_upcast_attn", "val": " = False"}, {"name": "**kwargs", "val": ""}]- **state_dim** (`int`, *optional*, defaults to 17) -- The state size for the RL environment - **act_dim** (`int`, *optional*, defaults to 4) -- The size of the output action space - **hidden_size** (`int`, *optional*, defaults to 128) -- The size of the hidden layers - **max_ep_len** (`int`, *optional*, defaults to 4096) -- The maximum length of an episode in the environment - **action_tanh** (`bool`, *optional*, defaults to True) -- Whether to use a tanh activation on action prediction - **vocab_size** (`int`, *optional*, defaults to 50257) -- Vocabulary size of the GPT-2 model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling `DecisionTransformerModel`. - **n_positions** (`int`, *optional*, defaults to 1024) -- The maximum sequence length that this model might ever be used with. Typically set this to something large just in case (e.g., 512 or 1024 or 2048). - **n_layer** (`int`, *optional*, defaults to 3) -- Number of hidden layers in the Transformer encoder. - **n_head** (`int`, *optional*, defaults to 1) -- Number of attention heads for each attention layer in the Transformer encoder. - **n_inner** (`int`, *optional*) -- Dimensionality of the inner feed-forward layers. If unset, will default to 4 times `n_embd`. - **activation_function** (`str`, *optional*, defaults to `"gelu"`) -- Activation function, to be selected in the list `["relu", "silu", "gelu", "tanh", "gelu_new"]`. - **resid_pdrop** (`float`, *optional*, defaults to 0.1) -- The dropout probability for all fully connected layers in the embeddings, encoder, and pooler. - **embd_pdrop** (`int`, *optional*, defaults to 0.1) -- The dropout ratio for the embeddings. - **attn_pdrop** (`float`, *optional*, defaults to 0.1) -- The dropout ratio for the attention. - **layer_norm_epsilon** (`float`, *optional*, defaults to 1e-5) -- The epsilon to use in the layer normalization layers. - **initializer_range** (`float`, *optional*, defaults to 0.02) -- The standard deviation of the truncated_normal_initializer for initializing all weight matrices. - **scale_attn_weights** (`bool`, *optional*, defaults to `True`) -- Scale attention weights by dividing by sqrt(hidden_size).. - **use_cache** (`bool`, *optional*, defaults to `True`) -- Whether or not the model should return the last key/values attentions (not used by all models). - **scale_attn_by_inverse_layer_idx** (`bool`, *optional*, defaults to `False`) -- Whether to additionally scale attention weights by `1 / layer_idx + 1`. - **reorder_and_upcast_attn** (`bool`, *optional*, defaults to `False`) -- Whether to scale keys (K) prior to computing attention (dot-product) and upcast attention dot-product/softmax to float() when training with mixed precision.0 This is the configuration class to store the configuration of a `DecisionTransformerModel`. It is used to instantiate a Decision Transformer model according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of the standard DecisionTransformer architecture. Many of the config options are used to instantiate the GPT2 model that is used as part of the architecture. Configuration objects inherit from [PretrainedConfig](/docs/transformers/v4.57.0/ja/main_classes/configuration#transformers.PretrainedConfig) and can be used to control the model outputs. Read the documentation from [PretrainedConfig](/docs/transformers/v4.57.0/ja/main_classes/configuration#transformers.PretrainedConfig) for more information. Example: ```python >>> from transformers import DecisionTransformerConfig, DecisionTransformerModel >>> # Initializing a DecisionTransformer configuration >>> configuration = DecisionTransformerConfig() >>> # Initializing a model (with random weights) from the configuration >>> model = DecisionTransformerModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```
## DecisionTransformerGPT2Model [[autodoc]] DecisionTransformerGPT2Model - forward ## DecisionTransformerModel [[autodoc]] DecisionTransformerModel - forward