Trajectory-Level Automatic Curriculum Learning for Legged Locomotion on Unstructured Terrain

• URL: http://arxiv.org/abs/2608.16164v1
• Date: Mon, 17 Aug 2026 06:30:45 GMT
• Title: Trajectory-Level Automatic Curriculum Learning for Legged Locomotion on Unstructured Terrain
• Abstract summary: textbfourname generates training tasks directly from unstructured terrain maps.<n>Our method improves success rate by (56.3%) over direct training without curriculum.
• Score: 30.327576375647663
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Training locomotion policies for complex unstructured terrain requires a curriculum to avoid early exploration failures. However, since unstructured terrain lacks explicit difficulty ordering for curriculum design, existing methods resort to heuristic curricula over parameterized terrains. This abstraction limits generalization, as policies can overadapt to near-fixed perceptual patterns. To address this, we propose \textbf{\ourname{}}, an \textbf{T}rajectory-level \textbf{A}utomatic \textbf{C}urriculum \textbf{L}earning framework that generates training tasks directly from unstructured terrain maps. At each curriculum update, the evaluator learns a difficulty function for the current policy that maps a given trajectory task to a difficulty score. The sampler then proposes new trajectories guided by the learned evaluator as the curriculum for the next policy update. This forms a closed loop in which the curriculum is iteratively matched to the evolving policy. Quantitative and qualitative experiments show that \ourname{} continuously provides effective curricula on unstructured terrain, improving trajectory success rate by \(56.3\%\) over direct training without curriculum. Compared with handcrafted curriculum learning, our method improves success rate by \(18.5\%\) on the hardest terrain tasks and by up to \(39.74\%\) when evaluating traversal from diverse approach directions on the same obstacle type.

Related papers

• Curriculum Learning as Transport: Understanding Curricula with Wasserstein Geodesics [11.91720769864227]
  We present Wasserstein curriculum paths, a simple framework that decouples factors by representing curricula as trajectories of training distributions over discrete difficulty levels.<n>Across a calibrated synthetic suite with 12 tasks and 33 difficulty axes, we use this framework to isolate the effects of ordering, matched exposure, endpoint smoothness, and pacing under fixed training budgets.
  arXiv  Detail & Related papers  (2026-09-08T17:39:16Z)
• Active Curriculum Refinement for Reinforcement Learning [13.591678342611964]
  PATH is a curriculum-learning framework that performs active learning over the curriculum graph.<n> PATH first expands coverage by sampling diverse curriculum paths and then reallocates training toward regions that remain unmastered.
  arXiv  Detail & Related papers  (2026-08-26T23:52:14Z)
• Mind Your Steps: A General Learning Framework for Accurate Humanoid Foothold Tracking [78.30338456206984]
  We introduce a novel framework for training general-purpose 3D foothold-tracking policies.<n>By dynamically providing footstep support through a goal sampler, this method enables the learned policy to be agnostic to specific terrains.<n>Our new target representation effectively mitigates challenges arising in the real world, such as noisy and inaccurate pose estimation and foot contact estimation.
  arXiv  Detail & Related papers  (2026-06-06T16:44:56Z)
• Provable Benefit of Curriculum in Transformer Tree-Reasoning Post-Training [76.12556589212666]
  We show that curriculum post-training avoids the exponential complexity bottleneck.<n>Under outcome-only reward signals, reinforcement learning finetuning achieves high accuracy with sample complexity.<n>We establish guarantees for test-time scaling, where curriculum-aware querying reduces both reward oracle calls and sampling cost from exponential to order.
  arXiv  Detail & Related papers  (2025-11-10T18:29:54Z)
• Efficient Mitigation of Bus Bunching through Setter-Based Curriculum Learning [0.47518865271427785]
  We propose a novel approach to curriculum learning that uses a Setter Model to automatically generate an action space, adversary strength, and bunching strength. Our method for automated curriculum learning involves a curriculum that is dynamically chosen and learned by an adversary network.
  arXiv  Detail & Related papers  (2024-05-23T18:26:55Z)
• RT-Trajectory: Robotic Task Generalization via Hindsight Trajectory Sketches [74.300116260004]
  Generalization remains one of the most important desiderata for robust robot learning systems. We propose a policy conditioning method using rough trajectory sketches. We show that RT-Trajectory is able to perform a wider range of tasks compared to language-conditioned and goal-conditioned policies.
  arXiv  Detail & Related papers  (2023-11-03T15:31:51Z)
• Learning Coverage Paths in Unknown Environments with Deep Reinforcement Learning [17.69984142788365]
  Coverage path planning ( CPP) is the problem of finding a path that covers the entire free space of a confined area. We investigate how suitable reinforcement learning is for this challenging problem. We propose a computationally feasible egocentric map representation based on frontiers, and a novel reward term based on total variation.
  arXiv  Detail & Related papers  (2023-06-29T14:32:06Z)
• Landmark Policy Optimization for Object Navigation Task [77.34726150561087]
  This work studies object goal navigation task, which involves navigating to the closest object related to the given semantic category in unseen environments. Recent works have shown significant achievements both in the end-to-end Reinforcement Learning approach and modular systems, but need a big step forward to be robust and optimal. We propose a hierarchical method that incorporates standard task formulation and additional area knowledge as landmarks, with a way to extract these landmarks.
  arXiv  Detail & Related papers  (2021-09-17T12:28:46Z)
• A Curriculum-style Self-training Approach for Source-Free Semantic Segmentation [91.13472029666312]
  We propose a curriculum-style self-training approach for source-free domain adaptive semantic segmentation. Our method yields state-of-the-art performance on source-free semantic segmentation tasks for both synthetic-to-real and adverse conditions.
  arXiv  Detail & Related papers  (2021-06-22T10:21:39Z)
• Curriculum Learning: A Survey [65.31516318260759]
  Curriculum learning strategies have been successfully employed in all areas of machine learning. We construct a taxonomy of curriculum learning approaches by hand, considering various classification criteria. We build a hierarchical tree of curriculum learning methods using an agglomerative clustering algorithm.
  arXiv  Detail & Related papers  (2021-01-25T20:08:32Z)
• Guided Curriculum Learning for Walking Over Complex Terrain [2.4192504570921622]
  We propose a 3-stage curriculum to train Deep Reinforcement Learning policies for bipedal walking over various challenging terrains. In simulation experiments, we show that our approach is effective in learning walking policies, separate from each other, for five terrain types.
  arXiv  Detail & Related papers  (2020-10-08T09:03:43Z)

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.