Mode d’emploi
- Copiez la commande et examinez le paquet avant de l’installer dans votre environnement agent.
- Consultez le document original pour les outils, identifiants et environnements requis.
- Décrivez les entrées et le livrable souhaité ; comparez la sortie aux sources.
npx skills add https://github.com/google-deepmind/robotics-antigravity-plugin --skill mujoco-playground-rlAvant de commencer
- L’installation n’inclut ni abonnement au modèle, ni quota API, ni accès aux fichiers.
- Étoiles et installations reflètent l’activité, pas un test indépendant de qualité ou de sécurité.
Rendu depuis le dépôt source en conservant titres, exemples, code, tableaux, liens et images.
MuJoCo Playground RL Task Authoring & Training (`rl_task_check.py`)
Create, interactively verify in MuJoCo Studio, audit, train (Impl.WARP + RSL-RL), and deploy new RL tasks on any mujoco_menagerie robot (floating-base quadrupeds/humanoids or fixed-base arms) in mujoco_playground:
- Workspace & Accelerator Setup:
- Clone and sync:
git clone https://github.com/google-deepmind/mujoco_playground.git && cd mujoco_playground && make sync(ormake sync-cu12on Linux CUDA 12 drivers< 580, ormake sync-cpuon macOS for authoring, Studio inspection, CPU smoke tests, and checkpoint playback; pass--default-index https://pypi.org/simpletouvand--no-synctouv run).
- Robot Scene, MuJoCo Studio Inspection, & `DeviceLayer` (`mujoco_playground/robots/<robot>/sim/{device,scene}.py`):
- Load
spec = asset.get("github:google-deepmind/mujoco_menagerie/<dir>/<file>.xml").spec(). Name unnamed geoms (f"{body.name}_geom_{i}"), ensure any freejoint is named ("root"), add a"terrain"plane geom onworldbodyif absent, setspec.option.timestep = 0.004(control_timestep = 0.02,decimation = 5) andmjINT_IMPLICITFAST, and sizecfg.sim.nconmax/cfg.sim.njmax(tolerance = 1e-8,ls_tolerance = 0.01, keeping default solver iteration caps). - Replace torque
<motor>s with PD position servos (for a in list(spec.actuators): spec.delete(a),add_actuator(name=j, target=j)withtrntype=mjTRN_JOINT,gaintype=mjGAIN_FIXED,biastype=mjBIAS_AFFINE,gainprm[0]=kp,biasprm[1]=-kp,biasprm[2]=-kd,ctrllimited=False,forcelimited=True,forcerange=[-effort, effort]; e.g.kp=25.0, kd=0.5, armature=0.01for quadrupeds), lower high passive torque-model jointdamping/frictionloss(e.g.damping=0.1, frictionloss=0.0), filter self-collisions viacontype/conaffinitybitmasks, and add an"init_state"standing keyframe. - **Interactive Studio Verification (
mujoco-studio-sidecar+
mujoco-studio): Load mujoco-studio-sidecar and mujoco-studio** to inspect and hot-reload the robot MjSpec (publishing the spec from SimPlugin.on_load_model in <workspace_dir>/sim_plugin.py, checking standing keyframe stability, PD gains, contacts, and custom ViewerPlugins) in [MuJoCo Studio](sidecar://robotics/mujoco_studio/) by launching <mujoco-studio-sidecar>/scripts/studiod.py --workspace_dir=<dir> with <playground_dir>/.venv/bin/python (IsDaemon: true, checking /_studio/status after edits) before batch training.
- Wire
reaf.simulation.torch(reaf_sim) devices viaflat_scene.Component(never passname=,nworld=, orxpu_device=): reaf_sim.ActuatorDevice(targets=list(JOINT_NAMES), measurements=["joint_pos", "joint_vel"])("robot"->"robot/ctrl","robot/joint_pos","robot/joint_vel").- Floating base:
reaf_sim.FreeDevice(body_name="base", joint_name="root", measurements=["xpos", "xquat", "joint_vel"])("base"->"base/xpos","base/xquat"[w,x,y,z], and"base/joint_vel"where[:, :3]is world linear velocity ->reaf_sim.math.quat_rotate_inverse(quat, vel[:, :3]), while[:, 3:6]is already body-frame angular velocity). - Contacts:
flat_scene.Component(reaf_sim.ContactSensorDevice, fields=("found", "force"), history_length=decimation).configure_spec(objtype="geom", objname=..., reftype="geom", refname="terrain")on feet and body/limb geoms.
- Sync-Free `TaskLayer` (`mujoco_playground/tasks/<category>/<task>/{task,mdp}.py`):
- Actions:
command_feature_producers={"action_history": flat_scene.Component(reaf_sim.ActionHistory, key="action", feature_shape=(num_joints,), history_length=1)}(f["action"]isa_t,f["action_history"][:, 0]isa_{t-1}) andcommand_processors={"action_scale": flat_scene.Component(reaf_sim.TransformActions, input_key="action", output_key="robot/ctrl", scale=0.25, offset=DEFAULT_JOINT_POS)}. - Stateful Producers & Observations: Subclass
reaf_sim.FeatureProducerimplementingname,produced_features_spec(per-world shapes withoutnworld),required_features_keys(consume"time"and step timers bydt = (t - self._last_time).clamp(min=0.0)so partial resets are idempotent),produce_features, andreset; wrap reward/critic-only producers with.mark_privileged()somake_deployment_configprunes them. - Sync-Free GPU Rules: Never call
.item(),.cpu(),.numpy(),.new_tensor(),bool(),.any(), or.all()insidestep/obs_*/reward_*; build gravity viag = torch.zeros((n, 3), device=q.device, dtype=q.dtype); g[:, 2] = -1.0and cache CPUflat_scene.Obstensor kwargs per(device, dtype). ConfigureObsGroups ("policy"noisy,"critic"clean) with.configure(output_shape=(D,))on everyflat_scene.Obs(actor: bodyang_vel,projected_gravity,command,joint_pos - default_pos,joint_vel,action; critic adds bodylin_vel). - Rewards, Terminations, & Reset: Combine
exp(-||v_xy - cmd_xy||^2 / 0.25)(1.5),exp(-(w_z - cmd_wz)^2 / 0.25)(0.75),v_z^2(-2.0),||w_xy||^2(-0.05),||g_proj_xy||^2(-2.5),||a_t - a_{t-1}||^2(-0.01),||qvel||^2(-1e-4), stand-still||q - q_def||_1 * (||cmd|| < 0.05)(-0.5), and undesired contacts (-1.0);FunctionalRewardProvidermultiplies terms bycontrol_dt, so divide touchdown impulses bycontrol_dt. Terminate on falls (g_proj[:, 2] > -0.3orz < min_z) viatorch.where(..., TerminationResult.TERMINATE, TerminationResult.DO_NOT_TERMINATE), and reset standingqpos/qvelinEnvironmentReset.on_resetviatorch.where(env_mask.unsqueeze(1), ...).
- Register, Validate, Train, Preview in Studio, & Deploy:
- Add an
RslRlOnPolicyRunnerCfgdataclass in_src/rl/rsl_rl/env_rl_config.py(obs_groups={"actor": ["policy"], "critic": ["critic"]},vecenv_wrapper_cfg=RslRlVecEnvWrappercfg(is_finite_horizon=False),nworld=4096,num_steps_per_env=24,actor/critic.hidden_dims=(256, 128, 128),obs_normalization=True) and register an uncalledenv_cfg_fnin_src/rl/env_registry.py. - Audit & smoke-test (CPU +
torch.cuda.set_sync_debug_mode("error")Impl.WARP+make_deployment_config):uv run --no-sync python <skill_dir>/scripts/rl_task_check.py --repo_root=. --task_dir=mujoco_playground/tasks/<category>/<task> --env_id=<EnvId>. - Train & preview in MuJoCo Studio:
WP_CACHE_PATH=/tmp/wp_cache uv run --no-sync python -m mujoco_playground.rl.rsl_rl.train --env=<EnvId> --wp_kernel_cache_dir=/tmp/wp_cache --logdir=/tmp/rslrl_logs/<run>. Preview checkpoints interactively in MuJoCo Studio viauv run --no-sync python -m mujoco_playground.rl.rsl_rl.play --env=<EnvId> --resume_path=... --gfx=web --hot_reload=plugins(or--gfx=""for native desktop Studio, authoring customViewerPlugins permujoco-studio), or deploy withflat_scene.make_deployment_config(cfg, observation_groups=("policy",))+wrapper.TorchDeviceLayerWrapper.