cs.LGJul 29, 2026

SCOUT: Per-Context Reset Curricula for Sparse-Reward Reinforcement Learning

Authors: Siddharth Aphale, Ayushman Singh

Organizations: Stanford University · Sesame AI

Abstract

Sparse-reward reinforcement learning often fails because rollouts from the unassisted evaluation start rarely reach later task stages. Reset curricula address this by starting some training rollouts from easier intermediate states, called scaffolds. Such a curriculum faces two decisions: scaffold access, obtaining informative starts, and scaffold allocation, deciding how quickly that assistance is removed. Most prior curricula pace removal on one shared schedule, which can fail when task instances, or contexts, learn at different rates. We introduce SCOUT, an online, learner-agnostic reset controller that gives every context its own curriculum. Using only binary rollout success, SCOUT removes assistance after sustained success, restores it after failure, and cautiously tests a harder start when progress stalls, without changing the reward, optimizer, or learner. A counting construction shows that synchronized global pacing can be insufficient when contexts need conflicting amounts of assisted practice. Across six navigation and manipulation settings, scaffold access improves learning and enables success in three where unassisted training fails within the reported budget. In a constructed pacing conflict, each tested global schedule leaves one group unsolved, while SCOUT solves both. Average success can conceal this failure, so we also report the least successful group. Group-level pacing works when learning differences follow known groups but can fail when they occur within one group. SCOUT needs no group labels and remains consistently strong in both cases. A reset curriculum should remove assistance at the scale where learning progress differs.

Explore similar work

CardsList
Aug 7, 2026cs.LG

Trajectory-Relative Hindsight Distillation for Agentic Reinforcement Learning

Recent agentic reinforcement learning methods use hindsight to complement sparse outcome rewards. However, a completed rollout can yield many such signals, leaving their appropriate allocation across turns unclear. We introduce TRIAL, a trajectory-relative hindsight distillation framework with a unified turn-aligned scoring protocol. For each decision turn, TRIAL extracts an outcome view of that decision's realized consequence and evaluates the same response under ordinary and hindsight-conditioned contexts. The signed log-probability gap determines the direction and local strength of token-level supervision, while turn-level magnitudes are normalized jointly over the realized trajectory. The resulting allocation multipliers have an eligible-token-weighted mean of one, redistributing dense supervision across turns while fixing its average multiplier. Experiments on WebShop and ALFWorld with different backbones show that TRIAL outperforms GRPO across all eight combinations of backbone, environment, and evaluation metric, while achieving the best or tied-best performance among six methods on six of them. On WebShop with Qwen3-1.7B, TRIAL improves the success rate from 56.4% to 75.2% and the task score from 78.7% to 85.7%. Controlled ablations further show that trajectory-relative turn allocation provides substantial gains beyond those of dense hindsight distillation alone.
Haoyu Zheng, Yun Zhu, Qing Wang +1
Agentic Reinforcement LearningHindsightDecisions
AskPDF
Mar 9, 2026cs.AI

Learning When to Trust in Contextual Social Bandits

Robust reinforcement learning typically assumes that feedback sources are either globally trustworthy or corrupted within a fixed global budget. We identify a more subtle failure mode that escapes this dichotomy, which we call \emph{Contextual Sycophancy}. In this failure, evaluators are truthful in benign contexts but systematically biased in critical ones, so that no single evaluator is reliable everywhere and the corrupt evaluators may form a \emph{majority} in the contexts that matter. Our first result is an information-theoretic lower bound. We exhibit two problem instances that induce \emph{identical} social-feedback distributions yet have disjoint optimal actions, proving that \emph{any} algorithm relying on social feedback alone (including any robust aggregator, regardless of breakdown point) incurs Ω(T)Ω(T) latent regret. This shows that breaking contextual sycophancy is impossible without having some information. We then show that a sparse stream of ground-truth audits, available with probability paudp_{\mathrm{aud}}, is sufficient. We propose \ESA, which learns a per-evaluator contextual \emph{trust boundary} from audits and re-weights feedback accordingly, and we prove a high-probability latent-regret bound of O~ ⁣(T dVC/paud+dT+εtolT)\tilde{\mathcal{O}}\!\big(\sqrt{T\,d_{VC}/p_{\mathrm{aud}}} + d\sqrt{T} + ε_{\mathrm{tol}}T\big), where dVCd_{VC} is the complexity of the adversary's bias strategy. The audit-dependence 1/paud1/\sqrt{p_{\mathrm{aud}}} matches the information-theoretic necessity of audits. Empirically, \ESA\ recovers the ground truth when 80%80\% of the social layer is adversarial, a regime in which median- and mean-based robust baselines fail.
Majid Ghasemi, Mark Crowley
Multi-Objective BanditsSycophancyAdaptive AdversaryAlgorithm Auditing
AskPDF
Aug 5, 2026cs.LG

Optimizing What Policies Learn From: Recoverability-aware Rollout Intervention Learning

Critic-free group-based reinforcement learning has become a scalable approach for post-training large language models. However, most existing methods allocate the same number of rollouts to every task and trajectory state, even though some rollouts provide much more useful learning signals than others. Recent work has started to treat rollout generation as an adaptive decision, but two important limitations remain. First, intervention strategies are often based on fixed heuristics and therefore cannot adjust as the policy changes during training. Second, these methods usually decide only how many rollouts to generate, without explicitly controlling where and how to intervene. To address these limitations, we propose Recoverability-Aware Intervention Learning (RAIL), a training-time framework that learns how to generate rollouts based on the improvement produced by each intervention. RAIL models intervention selection as an online contextual-bandit problem and trains a recoverability controller using intervention traces collected through a shadow-to-live procedure. This allows the controller to keep learning while the underlying policy evolves. We evaluate RAIL in terms of effectiveness, adaptivity, expressiveness, and efficiency. Across multiple settings, RAIL consistently improves performance under limited rollout budgets. These results show that recoverability-aware intervention provides a principled way to generate more informative and less redundant rollouts, leading to stronger learning signals during post-training.
Zheyuan Zhang, Manqing Mao, Hong Wang +8
Reinforcement Learning RolloutsRolloutCritic
AskPDF