[Task Clean-up][Manager] Dexterous Part 5/8: Add the reorientation manager counterparts#6418
[Task Clean-up][Manager] Dexterous Part 5/8: Add the reorientation manager counterparts#6418hujc7 wants to merge 4 commits into
Conversation
Greptile SummaryThis PR rewrites the Allegro Hand manager-based reorientation environment to match the Direct task's observation, action, reward, reset, termination, and success contracts, and adds a Newton physics preset. It lands the shared MDP terms (commands, events, observations, rewards, terminations) that the upcoming Shadow manager parts 9–11 will reuse.
Confidence Score: 4/5Safe to merge for the Allegro scope; the The Allegro config is solid and validated on both PhysX and Newton. The main concern is
Important Files Changed
|
![greptile-apps[bot]](https://avatars.githubusercontent.com/in/867647?s=60&v=4){kind=small}
| def direct_reorient_timeout( | ||
| env: ManagerBasedRLEnv, | ||
| command_name: str, | ||
| reward_name: str, | ||
| success_tolerance: float, | ||
| max_successes: int, | ||
| object_cfg: SceneEntityCfg = SceneEntityCfg("object"), | ||
| ) -> torch.Tensor: | ||
| """Apply the Direct OpenAI progress-reset and timeout semantics. | ||
|
|
||
| Args: | ||
| env: Environment containing the object, goal, and reward term. | ||
| command_name: Goal command term name. | ||
| reward_name: Reorientation reward term name. | ||
| success_tolerance: Goal orientation tolerance [rad]. | ||
| max_successes: Goals after which the episode terminates. | ||
| object_cfg: Object scene entity. | ||
|
|
||
| Returns: | ||
| Per-environment timeout flags. | ||
| """ | ||
| object_asset = env.scene[object_cfg.name] | ||
| target_quat = env.command_manager.get_command(command_name)[:, 3:7] | ||
| goal_reached, _ = evaluate_reorient_success(object_asset.data.root_quat_w.torch, target_quat, success_tolerance) | ||
| env.episode_length_buf = torch.where( | ||
| goal_reached, | ||
| torch.zeros_like(env.episode_length_buf), | ||
| env.episode_length_buf, | ||
| ) | ||
| reward_term: DirectReorientReward = env.reward_manager.get_term_cfg(reward_name).func | ||
| max_success_reached = reward_term.successes >= max_successes | ||
| return (env.episode_length_buf >= env.max_episode_length - 1) | max_success_reached |
There was a problem hiding this comment.
direct_reorient_timeout writes directly to env.episode_length_buf inside what the framework expects to be a stateless predicate. When a goal is reached the counter is zeroed, which effectively hides elapsed time from every other termination term evaluated after this one in the same step. If a second fall or out-of-reach termination runs after this one, the reset can mask conditions that had been accumulating. The function is not wired into the current Allegro config (direct_timeout is used instead), but the PR description states it will be adopted by the Shadow manager parts 9–11, so the risk will materialize.
| def reset(self, env_ids: Sequence[int] | None = None) -> None: | ||
| if env_ids is None: | ||
| env_ids = slice(None) | ||
| threshold = self.cfg.params["success_count_threshold"] | ||
| self._env.extras.setdefault("log", {})["Metrics/success_rate"] = ( | ||
| (self._successes[env_ids] >= threshold).float().mean().item() | ||
| ) | ||
| for statistic, value in self._orientation_error.reset(env_ids).items(): | ||
| self._env.extras["log"][f"Diagnostics/episode_min_orientation_error_{statistic}"] = value | ||
| self._successes[env_ids] = 0.0 |
There was a problem hiding this comment.
reset is called with only the env_ids terminating in the current step; when a fraction of environments reset, the logged Metrics/success_rate reflects only that fraction and overwrites any earlier value from the same training step. Training dashboards may see a highly-variable or systematically biased metric depending on the batch composition at each reset boundary. Consider always computing the mean over all envs (ignoring env_ids) so the logged value is representative of the full population.
|
|
||
|
|
||
| @configclass | ||
| class ObservationsCfg: | ||
| """Full 124-dimensional state observation in Direct order.""" | ||
|
|
There was a problem hiding this comment.
set_num_envs double-writes the physx backend via its default alias
self.default is the same Python object as self.physx (assigned by default = physx), so self.default.num_envs = num_envs and self.physx.num_envs = num_envs are redundant. The second assignment is a no-op today but could confuse readers or silently break if default is ever re-pointed to a different backend.
| @configclass | |
| class ObservationsCfg: | |
| """Full 124-dimensional state observation in Direct order.""" | |
| def set_num_envs(self, num_envs: int) -> None: | |
| """Set the environment count on every backend alternative.""" | |
| self.physx.num_envs = num_envs | |
| self.newton_mjwarp.num_envs = num_envs | |
| self.ovphysx.num_envs = num_envs | |
| self.default = self.physx |
Note: If this suggestion doesn't match your team's coding style, reply to this and let me know. I'll remember it for next time!
Add a behavioral Metrics/success_rate signal (goal-reach streaks per episode) and threshold-independent episode orientation-error diagnostics to the Direct reorientation environments, with the shared helpers in isaaclab_tasks.core.utils and torch math tests. The task logic is torch-first per the mainline convention; success gates task health while reward stays diagnostic. Also fix hand resets that could initialize joints below their lower position limits.
3b4f0cc to
d4d1290
Compare
hujc7
changed the title
hujc7
changed the title
…nager runtime (#6412) ## Summary - Fixes OVPhysX actuator joint indices to follow the common actuator indexing contract. - Fixes OVPhysX initialization alongside Kit by reusing Kit's registered PhysX schema provider. - Fixes the OVPhysX manager to support both the declared public runtime API and the current runtime API. - Regression tests included. Validated by full dexterous training runs on the OVPhysX backend; split out of the lumped validation branch #6324 (Part 2 of 11). ## Dependencies - None. ## Series review map Full integrated diff + training/validation evidence: the lumped validation PR #6324 (DO-NOT-MERGE). | Part | PR | |---|---| | Docs: regenerate the environment overview table | #6410 | | Part 1/11: Newton runtime fixes (cloner rows, cubric fallback, viz teardown) | #6411 | | **Part 2/11: OVPhysX runtime fixes (this PR)** | #6412 | | Part 3/11: success-rate metrics for the Direct reorientation tasks | #6413 | | Part 4/11: RSL-RL training for the handover Direct task | #6414 | | Part 5/11: success-rate support in the benchmark utilities | #6415 | | Part 6/11: renderer presets for the Direct camera task | #6416 | | Part 7/11: OVPhysX presets for the dexterous tasks | #6417 | | Part 8/11: Allegro manager counterpart | #6418 | | Part 9/11: Shadow + OpenAI manager counterparts | #6419 | | Part 10/11: Shadow camera manager counterpart | #6420 | | Part 11/11: Shadow handover manager counterpart | #6421 | --- ### Exact changes in this PR - OVPhysX backend changes + tests: 1f7a433
hujc7
changed the title
Fold the reviewed lump changes that belong to this part's content: - Share per-family sim settings through task-cfg base mixins. - Deduplicate backend scene presets via inner-class defaults and nest single-consumer helper cfgs in the shadow-hand Direct cfg. - Compute the orientation error through isaaclab.utils.math.quat_error_magnitude and delete the local direct_reorient_rotation_distance primitive. - Rename direct_reorient_reward to reorient_reward: shared symbols carry no paradigm prefix. Source commits on the lump branch: 2c22af0, 792e400, 42675b6, c6140f9, 173e9dc.
f8b3611 to
c5195e8
Compare
970a1cf to
da863b8
Compare
Part 3 share of the lump readability round (cdaadac): the Direct cfg files keep only task values; asset and marker cfgs, name lists, backend presets, and noise cfgs move to shadow_hand_common and allegro_hand_common, task geometry to reorient_common, and reorient_task_base is removed. The Shadow Direct files carry the workflow marker in their names.
Rebuilt from the reviewed lump so the manager counterparts land with the review rounds folded in: inline section values per file (drift guarded by the value-parity test incl. sim), identity from the common modules, the OpenAI variant in its own module, and no sim mixins. Lump review commits folded: 2c22af0, 792e400, 42675b6, 1f05f85, c6140f9, 173e9dc, 2727616, 1732493, 3659a33, ee272c9, cdaadac.
da863b8 to
957322a
Compare
1 participant
Review Map
Summary
ReorientObjectEnvCfgand its terms are deprecated in favor of the Direct-compatible ones.Stacking
Validation