View source on GitHub
|
Bandit related tensor spec utilities.
Functions
create_per_arm_observation_spec(...): Creates an observation spec with per-arm features and possibly action mask.
drop_arm_observation(...): Drops the per-arm observation from a given trajectory (or trajectory spec).
get_context_dims_from_spec(...): Returns the global and per-arm context dimensions.
Other Members | |
|---|---|
| CONSTRAINTS_SPEC_KEY |
'constraint'
|
| GLOBAL_FEATURE_KEY |
'global'
|
| NUM_ACTIONS_FEATURE_KEY |
'num_actions'
|
| PER_ARM_FEATURE_KEY |
'per_arm'
|
| REWARD_SPEC_KEY |
'reward'
|