A float tensor of shape [outer_dim1, ... outer_dimK, action_dim1,
..., action_dimJ].
actions
An int tensor of shape [outer_dim1, ... outer_dimK] if
multi_dim_actions=False [outer_dim1, ... outer_dimK, J] if
multi_dim_actions=True I.e. in the multidimensional case,
actions[outer_dim1, ... outer_dimK] is a vector [actions_1, ...,
actions_J] where each element actions_j is an action in the range [0,
num_actions_j). While in the single dimensional case, actions[outer_dim1,
... outer_dimK] is a scalar.
multi_dim_actions
whether the actions are multidimensional.
Returns
A [outer_dim1, ... outer_dimK] tensor of q_values for the given actions.
[null,null,["Last updated 2024-04-26 UTC."],[],[],null,["# tf_agents.utils.common.index_with_actions\n\n\u003cbr /\u003e\n\n|----------------------------------------------------------------------------------------------------------------|\n| [View source on GitHub](https://github.com/tensorflow/agents/blob/v0.19.0/tf_agents/utils/common.py#L368-L412) |\n\nIndex into q_values using actions. \n\n tf_agents.utils.common.index_with_actions(\n q_values, actions, multi_dim_actions=False\n )\n\n| **Note:** this supports multiple outer dimensions (e.g. time, batch etc).\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Args ---- ||\n|---------------------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| `q_values` | A float tensor of shape \\[outer_dim1, ... outer_dimK, action_dim1, ..., action_dimJ\\]. |\n| `actions` | An int tensor of shape \\[outer_dim1, ... outer_dimK\\] if multi_dim_actions=False \\[outer_dim1, ... outer_dimK, J\\] if multi_dim_actions=True I.e. in the multidimensional case, actions\\[outer_dim1, ... outer_dimK\\] is a vector \\[actions_1, ..., actions_J\\] where each element actions_j is an action in the range \\[0, num_actions_j). While in the single dimensional case, actions\\[outer_dim1, ... outer_dimK\\] is a scalar. |\n| `multi_dim_actions` | whether the actions are multidimensional. |\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Returns ------- ||\n|---|---|\n| A \\[outer_dim1, ... outer_dimK\\] tensor of q_values for the given actions. ||\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Raises ------ ||\n|--------------|-------------------------------|\n| `ValueError` | If actions have unknown rank. |\n\n\u003cbr /\u003e"]]
View source on GitHub
