Multi-scale Predictive Representations for Goal-conditioned Reinforcement Learning

• URL: http://arxiv.org/abs/2605.09364v1
• Date: Sun, 10 May 2026 06:27:20 GMT
• Title: Multi-scale Predictive Representations for Goal-conditioned Reinforcement Learning
• Abstract summary: Ms.PR is a framework that leverages multi-scale predictive supervision to enforce goal-directed alignment within the latent space.<n>We demonstrate that Ms.PR leads to improved representation quality and strong performance on both vision and state-based tasks.
• Score: 16.445856792021726
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This paper investigates robust representation learning in offline goal-conditioned reinforcement learning (GCRL). Particularly in sparse reward scenarios, learning representations that align state and goal latents is a challenge that frequently culminates in representation divergence where the encoder drifts toward a low-dimensional, goal-agnostic subspace that destabilizes policy learning. We address this issue by showing that an agent must acquire a fundamental understanding of its environment across multiple scales, from local physical dynamics to long-horizon goal-directed structure. Building on this insight, we propose Ms.PR, a framework that leverages multi-scale predictive supervision to enforce goal-directed alignment within the latent space. We demonstrate that Ms.PR leads to improved representation quality and strong performance on both vision and state-based tasks. Furthermore, we show that our approach is exceptionally resilient under realistic, challenging data regimes, maintaining state-of-the-art performance across a wide variety of tasks, trajectory stitching scenarios, and extreme noise conditions.

Related papers

• Towards Predictive, Aligned, and Scalable Robot Learning [11.830982964522605]
  We introduce Lumo-2, a latent world-action model that generates actions by reasoning over world dynamics in latent space.<n>We study latent world modelling and modality alignment, analyzing their roles in scaling laws and out-of-distribution generalization.<n>Results show that Lumo-2 consistently outperforms strong vision-language-action (VLA) and world-action model (WAM) baselines.
  arXiv  Detail & Related papers  (2026-07-13T08:53:34Z)
• From Holistic Evaluation to Structured Criteria: Rubrics Across the Evolving LLM Landscape [79.30826980815927]
  rubrics are explicit criteria sets that transform complex quality judgments into structured and actionable standards.<n>We systematically organize existing rubric designs, examine their construction and optimization, and analyze their role across evaluation and training.
  arXiv  Detail & Related papers  (2026-06-07T13:34:55Z)
• PRTS: A Primitive Reasoning and Tasking System via Contrastive Representations [66.94988600664574]
  We present textbfPRTS (textbfPrimitive textbfReasoning and textbfTasking textbfSystem), a VLA foundation model that reformulates pretraining through Goal-Conditioned Reinforcement Learning.
  arXiv  Detail & Related papers  (2026-04-30T06:14:02Z)
• Regularized Latent Dynamics Prediction is a Strong Baseline For Behavioral Foundation Models [35.088440282359024]
  Behavioral Foundation Models (BFMs) produce agents with the capability to adapt to any unknown reward or task.<n>These methods are only able to produce near-optimal policies for the reward functions that are in the span of some pre-existing state features.<n>We propose an approach, Regularized Latent Dynamics Prediction (RLDP), that can match or surpass state-of-the-art complex representation learning methods for zero-shot RL.
  arXiv  Detail & Related papers  (2026-03-16T19:39:27Z)
• A Behavioural and Representational Evaluation of Goal-Directedness in Language Model Agents [8.007212170802807]
  We propose a framework for evaluating goal-directedness that integrates behavioural evaluation with interpretability-based analyses of models' internal representations.<n>We evaluate an agent against an optimal policy across varying grid sizes, obstacle densities, and goal structures.<n>We then use probing methods to decode the agent's internal representations of the environment state and its multi-step action plans.
  arXiv  Detail & Related papers  (2026-02-09T18:00:28Z)
• Revisiting Multi-Task Visual Representation Learning [52.93947931352643]
  We introduce MTV, a principled multi-task visual pretraining framework.<n>We leverage high-capacity "expert" models to synthesize dense, structured pseudo-labels at scale.<n>Our results demonstrate that MTV achieves "best-of-both-worlds" performance.
  arXiv  Detail & Related papers  (2026-01-20T11:59:19Z)
• PosA-VLA: Enhancing Action Generation via Pose-Conditioned Anchor Attention [92.85371254435074]
  PosA-VLA framework anchors visual attention via pose-conditioned supervision, consistently guiding the model's perception toward task-relevant regions.<n>We show that our method executes embodied tasks with precise and time-efficient behavior across diverse robotic manipulation benchmarks.
  arXiv  Detail & Related papers  (2025-12-03T12:14:29Z)
• Patch-Level Kernel Alignment for Dense Self-Supervised Learning [7.5866326278176075]
  We introduce Patch-level Kernel Alignment (PaKA), a non-parametric, kernel-based approach that improves the dense representations of pretrained vision encoders with a post-(pre)training.<n>Our framework improves dense representations by conducting a lightweight post-training stage on top of a pretrained model.<n>With only 14 hours of additional training on a single GPU, our method achieves state-of-the-art performance across a range of dense vision benchmarks.
  arXiv  Detail & Related papers  (2025-09-06T05:42:32Z)
• Rich-Observation Reinforcement Learning with Continuous Latent Dynamics [43.84391209459658]
  We introduce a new theoretical framework, RichCLD (Rich-Observation RL with Continuous Latent Dynamics), in which the agent performs control based on high-dimensional observations. Our main contribution is a new algorithm for this setting that is provably statistically and computationally efficient.
  arXiv  Detail & Related papers  (2024-05-29T17:02:49Z)
• Discrete Factorial Representations as an Abstraction for Goal Conditioned Reinforcement Learning [99.38163119531745]
  We show that applying a discretizing bottleneck can improve performance in goal-conditioned RL setups. We experimentally prove the expected return on out-of-distribution goals, while still allowing for specifying goals with expressive structure.
  arXiv  Detail & Related papers  (2022-11-01T03:31:43Z)
• Efficient Hierarchical Exploration with Stable Subgoal Representation Learning [26.537055962523162]
  We propose a state-specific regularization that stabilizes subgoal embeddings in well-explored areas. We develop an efficient hierarchical exploration strategy that actively seeks out new promising subgoals and states.
  arXiv  Detail & Related papers  (2021-05-31T07:28:59Z)
• Goal-Aware Prediction: Learning to Model What Matters [105.43098326577434]
  One of the fundamental challenges in using a learned forward dynamics model is the mismatch between the objective of the learned model and that of the downstream planner or policy. We propose to direct prediction towards task relevant information, enabling the model to be aware of the current task and encouraging it to only model relevant quantities of the state space. We find that our method more effectively models the relevant parts of the scene conditioned on the goal, and as a result outperforms standard task-agnostic dynamics models and model-free reinforcement learning.
  arXiv  Detail & Related papers  (2020-07-14T16:42:59Z)

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.