unilab.dr.provider.DomainRandomizationProvider

class unilab.dr.provider.DomainRandomizationProvider[source]

Bases: ABC

Methods

__init__()

build_init_randomization_plan(env)

build_interval_randomization_plan(env, ...)

Build the interval randomization plan for the upcoming step.

build_reset_observation(env, env_ids, ...)

build_reset_plan(env, env_ids)

validate(env, capabilities)

abstract validate(env, capabilities)[source]
Parameters:
Return type:

None

build_init_randomization_plan(env)[source]
Parameters:

env (Any)

Return type:

InitRandomizationPlan | None

abstract build_reset_plan(env, env_ids)[source]
Parameters:
Return type:

ResetPlan

abstract build_reset_observation(env, env_ids, info_updates)[source]
Parameters:
Return type:

dict[str, ndarray]

build_interval_randomization_plan(env, step_counter)[source]

Build the interval randomization plan for the upcoming step.

Populate the plan’s ops tuple with IntervalTermOp entries. Returning plans via the legacy fields (push_perturbation_limit, body_ids, body_linear_velocity_delta, body_angular_velocity_delta, body_force, body_torque) is deprecated: they are still adapted 1:1 through IntervalRandomizationPlan.iter_ops(), but they will be removed in the next unisim-core major release.

Parameters:

  • env (Any)

  • step_counter (int)

Return type:

IntervalRandomizationPlan | None