Experiments#

ProtoMotions implements several state-of-the-art algorithms for physics-based character animation. This page provides a high-level overview of each approach and when to use them.

Mimic#

Paper: DeepMimic: Example-Guided Deep Reinforcement Learning of Physics-Based Character Skills (Peng et al., 2018)

Mimic trains agents to imitate reference motion clips through reinforcement learning. The agent receives rewards for matching the reference pose at each timestep, learning to reproduce the motion while maintaining physical plausibility.

Experiment Variants:

  • mlp.py - MLP policy for flat terrain

  • mlp_complex_terrain.py - MLP policy for complex terrains (stairs, slopes, etc.)

  • mlp_bm_l2c2.py - BeyondMimic policy with a torso anchor and L2C2 smoothness regularization, aimed at sim2real

  • fsq.py - FSQ tracker over max-coordinates proprioception and target poses

The BM recipe uses q_target = q_default + 0.25 * effort_limit / stiffness * action without clipping the raw action or changing the robot’s PD gains. Its action-rate reward is -0.1 * sum((action - previous_action)**2) on raw policy outputs, with no mean, square root, or timestep division. This is distinct from the L2C2 model loss and from the processed-action L2 norm used by other recipes.

The scale change applies to all newly built configs using make_bm_pd_action_config. The raw action-rate reward is selected explicitly by the BM L2C2 recipe; other recipes keep their existing reward bindings. Resume and inference use the action scales and reward bindings saved in resolved_configs.pt; existing pretrained configs are not rewritten. Use a new experiment name to train with this recipe.

Example command:

python protomotions/train_agent.py \
    --experiment-path examples/experiments/mimic/mlp.py \
    --robot-name smpl \
    --simulator isaacgym \
    --motion-file <path_to_motion_file> \
    --experiment-name smpl_mimic

ADD (Adversarial Differential Discriminators)#

Paper: ADD: Physics-Based Motion Imitation with Adversarial Differential Discriminators

ADD is an adversarial approach to motion tracking that automatically balances multiple tracking objectives without manual reward weight tuning. It uses a discriminator to learn how to combine tracking errors dynamically.

Example command:

python protomotions/train_agent.py \
    --experiment-path examples/experiments/add/mlp.py \
    --robot-name smpl \
    --simulator isaacgym \
    --motion-file <path_to_motion_file> \
    --experiment-name smpl_add

MaskedMimic#

Paper: MaskedMimic: Unified Physics-Based Character Control Through Masked Motion Inpainting (Tessler et al., SIGGRAPH Asia 2024)

MaskedMimic formulates character control as a motion inpainting problem. A single unified controller learns to synthesize full-body motions from partial observations (masked keyframes, text descriptions, or scene information).

Note

MaskedMimic requires a pre-trained Mimic expert model. First, train Mimic on multiple motions, then provide the checkpoint path via --overrides.

Example command:

python protomotions/train_agent.py \
    --experiment-path examples/experiments/masked_mimic/transformer.py \
    --robot-name smpl \
    --simulator isaacgym \
    --motion-file <path_to_motions> \
    --overrides "agent.config.expert_model_path='<path_to_expert_model>/last.ckpt'" \
    --experiment-name smpl_masked_mimic

GPC and PEFT#

GPC trains a reusable discrete latent prior from tracker-derived FSQ tokens, then adapts the frozen prior to task skills with parameter-efficient fine-tuning. Use this path when you want a reusable generative motion prior that can be specialized with SFT, RLFT, or RLFT+AMP adapters.

See GPC and PEFT for the staged tracker, prior, SFT, RLFT, checkpoint, and inference workflow.

Unconditional GPC prior
Location task after PEFT

AMP (Adversarial Motion Priors)#

Paper: AMP: Adversarial Motion Priors for Stylized Physics-Based Character Control (Peng et al., 2021)

AMP uses a discriminator to learn a motion prior from reference data. Instead of tracking specific poses, the agent learns to move in a style similar to the reference motions while accomplishing task objectives.

Example command:

python protomotions/train_agent.py \
    --experiment-path examples/experiments/amp/mlp.py \
    --robot-name g1 \
    --simulator isaacgym \
    --motion-file <path_to_motion> \
    --experiment-name g1_amp

Steering#

Steering combines AMP-style motion priors with directional control objectives. The agent learns to walk/run in user-specified directions while maintaining natural motion style.

Example command:

python protomotions/train_agent.py \
    --experiment-path examples/experiments/steering/mlp.py \
    --robot-name g1 \
    --simulator isaacgym \
    --motion-file <path_to_motion> \
    --experiment-name g1_steering

ASE (Adversarial Skill Embeddings)#

Paper: ASE: Large-Scale Reusable Adversarial Skill Embeddings for Physically Simulated Characters (Peng et al., 2022)

ASE extends AMP by learning a latent skill space. The policy is conditioned on latent codes, allowing a single controller to perform many different skills by varying the latent input.

Note

ASE requires a diverse motion dataset with many different motion types. It does not work with a single motion clip - the skill embedding relies on having varied behaviors to learn meaningful latent codes.

Example command:

python protomotions/train_agent.py \
    --experiment-path examples/experiments/ase/mlp.py \
    --robot-name smpl \
    --simulator isaacgym \
    --motion-file <path_to_motions> \
    --experiment-name smpl_ase

See Also#