rlmesh.adapters.resolve

functionfrom rlmesh.adapters import resolve[source]

Derive an Adapter for an env/model pair.

resolve(
    env_tags: EnvTags,
    observation_space: object,
    action_space: object,
    model_spec: ModelSpec,
    *,
    trust_entrypoints: bool = False,
    check_inverse: bool = True,
) -> Adapter

Parameters

Name	Type	Description
`env_tags`	`EnvTags`	The environment's observation/action tags.
`observation_space`	`object`	The environment's gymnasium observation space (or any space object RLMesh can parse, e.g. an `rlmesh.spaces` space or a native `SpaceSpec`).
`action_space`	`object`	The environment's gymnasium action space.
`model_spec`	`ModelSpec`	The model's declared input/output format.
`trust_entrypoints`	`bool`	Allow `module:callable` strings in custom inputs to be imported. Leave False for specs from untrusted sources; in-process callables are always allowed. (Custom-encoding entrypoint arms are never run -- a custom encoding executes only where its in-process callable was defined.)
`check_inverse`	`bool`	Round-trip each two-armed `CustomEncoding` on a probe at resolve time to catch a mispaired encode/decode. Set False for an intentionally non-invertible encoding.

Returns

Type	Description
`Adapter`	Adapter applying observation preprocessing and action postprocessing.

Raises

Type	Description
`AdapterResolutionError`	If a model input or action component has no usable counterpart in the env tags and spaces.