HaM-World: Soft-Hamiltonian World Models with Selective Memory for Planning

• URL: http://arxiv.org/abs/2605.05951v1
• Date: Thu, 07 May 2026 09:58:18 GMT
• Title: HaM-World: Soft-Hamiltonian World Models with Selective Memory for Planning
• Abstract summary: HaM-World is a structured world model that decomposes the latent state into a canonical (q, p) subspace and a context subspace c.<n>On four DeepMind Control Suite tasks, HaM-World reaches the highest Avg. AUC (117.9, +9.5%), reduces long-horizon rollout error to 45% of a strong baseline model, and wins 11/12 k in 3,5,7 MSE cells.
• Score: 2.28917458387011
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: World models enable model-based planning through learned latent dynamics, but imagined rollouts become unstable as the planning horizon grows or the dynamics distribution shifts. We argue that this instability reflects two missing structures in planner-facing latents: history-conditioned memory for approximate Markov completeness, and geometric organization that separates configuration, momentum, and task semantics. We propose HaM-World (HMW), a structured world model that decomposes the latent state into a canonical (q, p) subspace and a context subspace c, while using Mamba selective state-space memory as the history-conditioned input to the same latent dynamics. Within this interface, (q, p) evolves through an energy-derived Hamiltonian vector field plus learnable residual/control dynamics, while c captures semantic, dissipative, and non-conservative factors. This gives the planner a single latent state shared by dynamics prediction, reward/value estimation, imagined rollouts, and CEM action search. On four DeepMind Control Suite tasks, HaM-World reaches the highest Avg. AUC (117.9, +9.5%), reduces long-horizon rollout error to 45% of a strong baseline model, and wins 11/12 k in {3,5,7} MSE cells. Under 12 OOD perturbations spanning dynamics shifts, action delay, and observation masking, HaM-World achieves the highest return in every condition, with average OOD-return gains of 10.2% on Finger Spin and 13.6% on Reacher Easy. Mechanism diagnostics further show bounded action-free Hamiltonian-energy drift, structured energy variation under policy rollouts, and coherent control-induced energy transfer, supporting the intended Soft-Hamiltonian dynamics design.

Related papers

• Semigroup-JEPA: Latent Dynamics Consistency for Zero-Shot Physics Generalization [32.65135632960651]
  Joint-Embedding Predictive Architecture (JEPA) world models learn a compact latent representation of the world that supports prediction and planning.<n>We introduce SemiGroup-JEPA, which extends the LeWorldModel framework by supplying the parameter governing the physics to the temporal model.<n>We design dynamical tasks under different gravitational fields that, despite obeying the same physical law, exhibit qualitatively different dynamics.
  arXiv  Detail & Related papers  (2026-09-09T17:08:13Z)
• Toward Physically Grounded JEPA World Models for Goal-Conditioned Robotic Planning [17.909802735976466]
  We introduce an end-to-end JEPA world model that augments latent prediction with inverse dynamics (IDM) and state alignment (SA)<n>Our model attains the highest success rates on TwoRoom (100%), PushT (98%), and OGBench-Cube (87%), while performing comparably to LeWorldModel on Reacher.
  arXiv  Detail & Related papers  (2026-09-03T09:11:13Z)
• Sensorimotor World Models: Perception for Action via Inverse Dynamics [59.121736411156384]
  We introduce a sensorimotor world model trained end-to-end with inverse dynamics regularization.<n>It prevents representation collapse and induces action-aligned representations.<n>It learns compact, interpretable latent spaces and enables competitive planning performance across simple 2D and 3D control tasks.
  arXiv  Detail & Related papers  (2026-06-18T11:25:16Z)
• PH-Dreamer: A Physics-Driven World Model via Port-Hamiltonian Generative Dynamics [0.0]
  World models built on recurrent state space architectures produce dynamics that violate conservation and dissipative principles.<n>We introduce a unified Port-Hamiltonian framework that remedies this through three synergistic mechanisms.<n>Across visual control benchmarks, this paradigm not only attains superior returns but also elevates internal fidelity by establishing a tighter, lower variance alignment between imagined and real rewards, all while reducing latent phase space volume by 4.18-8.41%, energy consumption by up to 7.80%, and mean squared jerk by up to 9.38%.
  arXiv  Detail & Related papers  (2026-05-18T12:20:54Z)
• STRIDE: Structured Lagrangian and Stochastic Residual Dynamics via Flow Matching [2.5845893156827158]
  We propose STRIDE, a dynamics learning framework that separates conservative rigid-body mechanics from uncertain, effectively non-conservative interaction effects.<n>We evaluate STRIDE on systems of increasing complexity, including a pendulum, the Unitree Go1ruped, and the Unitree G1 humanoid.<n>Results show 20% reduction in long-horizon prediction error and 30% reduction in contact force prediction error compared to deterministic residual baselines.
  arXiv  Detail & Related papers  (2026-03-09T15:15:21Z)
• Infinite-World: Scaling Interactive World Models to 1000-Frame Horizons via Pose-Free Hierarchical Memory [101.2076718776139]
  We propose a robust interactive world model capable of maintaining coherent visual memory over 1000+ frames in complex real-world environments.<n>We introduce a Pose-free Memory (HPMC) that distills historical latents into a fixed-budget geometric representation.<n>We also propose an Uncertainty-aware Action Labeling module that discretizes continuous motion into a tri-state logic.
  arXiv  Detail & Related papers  (2026-02-02T17:52:56Z)
• Scalable Spatio-Temporal SE(3) Diffusion for Long-Horizon Protein Dynamics [51.85385061275941]
  Molecular dynamics (MD) simulations remain the gold standard for studying protein dynamics.<n>Recent generative models have shown promise in accelerating simulations, yet they struggle with long-horizon generation.<n>We present STAR-MD, a scalable diffusion model that generates physically plausible protein trajectories over micro-scale timescales.
  arXiv  Detail & Related papers  (2026-02-02T14:13:28Z)
• Prismatic World Model: Learning Compositional Dynamics for Planning in Hybrid Systems [38.4555621948915]
  Prismatic World Model (PRISM-WM) is designed to decompose complex hybrid dynamics into composable primitives.<n>PRISM-WM significantly reduces rollout drift by accurately modeling sharp mode transitions in system dynamics.
  arXiv  Detail & Related papers  (2025-12-09T09:40:34Z)
• Agentic World Modeling for 6G: Near-Real-Time Generative State-Space Reasoning [70.56067503630486]
  We argue that sixth-generation (6G) intelligence is not fluent token prediction but calibrated the capacity to imagine and choose.<n>We show that WM-MS3M cuts mean absolute error (MAE) by 1.69% versus MS3M with 32% fewer parameters and similar latency, and achieves 35-80% lower root mean squared error (RMSE) than attention/hybrid baselines with 2.3-4.1x faster inference.
  arXiv  Detail & Related papers  (2025-11-04T17:22:22Z)
• Simplifying Latent Dynamics with Softly State-Invariant World Models [10.722955763425228]
  We introduce the Parsimonious Latent Space Model (PLSM), a world model that regularizes the latent dynamics to make the effect of the agent's actions more predictable. We find that our regularization improves accuracy, generalization, and performance in downstream tasks.
  arXiv  Detail & Related papers  (2024-01-31T13:52:11Z)
• SyMetric: Measuring the Quality of Learnt Hamiltonian Dynamics Inferred from Vision [73.26414295633846]
  A recently proposed class of models attempts to learn latent dynamics from high-dimensional observations. Existing methods rely on image reconstruction quality, which does not always reflect the quality of the learnt latent dynamics. We develop a set of new measures, including a binary indicator of whether the underlying Hamiltonian dynamics have been faithfully captured.
  arXiv  Detail & Related papers  (2021-11-10T23:26:58Z)
• Autoregressive Dynamics Models for Offline Policy Evaluation and Optimization [60.73540999409032]
  We show that expressive autoregressive dynamics models generate different dimensions of the next state and reward sequentially conditioned on previous dimensions. We also show that autoregressive dynamics models are useful for offline policy optimization by serving as a way to enrich the replay buffer.
  arXiv  Detail & Related papers  (2021-04-28T16:48:44Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.