Searcharxiv⌕ Search

arXiv subjects

Shangtong Zhang

Publications and source records attributed to Shangtong Zhang.

At least 19 recordsLinked to original sources

Latent Q-Barrier Shielding for Safe In-Context Reinforcement Learning

Safe in-context reinforcement learning (ICRL) adapts online from interaction history without test-time parameter updates while controlling episode cost under a safety budget. Under out-of-distribution (OOD) deployment shifts, pretraining-only safe ICRL can give poor reward-safety tradeoffs because the remaining budget affects behavior only through frozen policy conditioning, not an explicit action-level check against predicted future cost. We propose a latent Q-Barrier shield that learns a context representation, latent dynamics, and an ensemble cost critic before deployment. Without parameter updates, the shield infers context from history and filters or softly reweights candidate actions using the remaining budget and predicted future cost. We prove a conditional one-step barrier-margin bound over realized candidate sets, with explicit Bellman and latent-prediction error terms. Across five safe ICRL benchmarks, the shield improves deployment-time reward-safety tradeoffs over a strong safe-ICRL baseline: after a short context window, it achieves higher return in four of five benchmarks while matching or lowering average episode cost in all five. Code is available at https://github.com/kmj1122/q-barrier.

cs.LG↗

Algorithm Distillation for Safe In-Context Reinforcement Learning

Safe in-context reinforcement learning (Safe ICRL) asks a policy with fixed parameters to improve on an unseen constrained task from its interaction history while aiming to keep its cost within a budget. Prior work studied Safe ICRL on five benchmarks in three families: a grid world with a hidden goal and obstacles (DarkRoom), continuous navigation where goals and hazards stay invisible until reached (PointGoal, CarGoal), and locomotion with a hidden velocity limit (HalfCheetah, Ant). Safe Algorithm Distillation (Safe AD), trained on the learning histories of a safe RL algorithm, has shown adaptation failures in prior evaluations. For example, in the locomotion tasks its return stays below zero, and it rarely reaches the goal in CarGoal. We revisit two parts of Safe AD. First, we distill a budget-aware teacher with two phases. It searches for the hidden task, exploring more when more budget remains. After its first reward or cost, an expert policy exploits the task within the remaining budget. We collect the teacher's histories under fixed or dynamic budgets. Dynamic budgets increase the occupancy entropy of the return and budget inputs in every environment, and at test time they improve return and lower cost in DarkRoom and HalfCheetah. Second, we propose A-Lag, a test-time adjustment that reweights the distilled policy's actions by their predicted cost, with an adaptive Lagrange multiplier that is updated from the costs observed. In our experiments, A-Lag had lower mean episode cost than Safe AD in all five environments, with lower mean final return in four.

cs.LG↗

Almost Sure Convergence Rates of Stochastic Approximation and Reinforcement Learning via a Poisson-Moreau Drift

Establishing almost sure convergence rates for stochastic approximation and reinforcement learning under Markovian noise is a fundamental theoretical challenge. We make progress towards this challenge for a class of stochastic approximation algorithms whose expected updates are contractive, a setting that arises in many reinforcement learning algorithms such as $Q$-learning and linear temporal difference learning. Specifically, for a power-law learning rate $O(n^{-η})$ with $η\in (1/2, 1)$, we obtain an almost sure convergence rate arbitrarily close to $o(n^{1 - 2η})$. For the harmonic learning rate $α_n=α/(n+1)$, the almost sure squared-error rate is $o(n^{-ζ})$ for every $ζ<\min\{1,2(1-κ)α\}$, where $κ$ is the contraction factor. Thus exponents arbitrarily close to one are available when $2(1-κ)α\geq1$. This approaches the $n^{-1}$ polynomial exponent of classical law-of-the-iterated-logarithm benchmarks. Key to our analysis is a novel Lyapunov drift construction that applies a Poisson-equation based correction for Markovian noise to the well-established Moreau-envelope smoothing for the contractive mapping.

cs.LG↗

On the Divergence of Differential Temporal Difference Learning without Local Clocks

Learning rate is a critical component of reinforcement learning (RL). This work uses global and local clocks to distinguish two types of learning rates. The former is of the standard form $α_t$ that depends only on the time step $t$ (i.e., a global clock). The latter is of the form $α_{ν(S_t, t)}$, where $ν(s, t)$ counts the number of visits to state $s$ until time $t$ (i.e., a local clock). In discounted RL, an RL algorithm that is convergent with a local clock is always also convergent with a global clock, and vice versa. We are not aware of any counterexample. The key contribution of this work is to show that this nice correspondence breaks down in average-reward RL. Specifically, we construct a counterexample showing that although differential temporal difference (TD) learning is convergent with a local clock, it can diverge with a global clock. We empirically observe this divergence in our experiments and also prove that the associated ODE of differential TD with a global clock is unstable. This counterexample closes the open problem in Wan et al. [2021], Blaser et al. [2026].

cs.LG↗

MathlibPR: Pull Request Merge-Outcome Benchmark for Formal Mathematical Libraries

The ecosystem of Lean and Mathlib has become the de facto standard for large language model (LLM) assisted formal reasoning with remarkable successes in recent years. Those successes, however, only consume Mathlib as an essential dependency but do not directly contribute to it. In the meantime, the growth of Mathlib has recently been bottlenecked by the review process, which requires human reviewers to judge whether proposed pull requests (PRs) follow the Mathlib's conventions and are worth integrating as part of a shared mathematical infrastructure. This leads to our central question: can LLMs help review Mathlib PRs? To this end, we introduce MathlibPR, a benchmark built from real Mathlib4 PR histories. We further propose a staged evaluation protocol and use it to evaluate both LLM models (e.g., DeepSeek, Qwen, Goedel, and Kimina) and LLM agents (e.g., Codex and Claude Code). Surprisingly, both LLM models and LLM agents struggle to distinguish merge-ready PRs from build-passing PRs that were revised or never merged. By turning Mathlib PR histories into a supervised signal, MathlibPR provides a step toward reviewer assistants and reward models that could help evaluate PRs and steer LLMs toward producing merge-ready Mathlib contributions.

cs.LO↗

Efficient Policy Evaluation with Offline Data Informed Behavior Policy Design

Online Monte Carlo evaluation is a fundamental tool for assessing policy performance in reinforcement learning and sequential decision-making problems arising in operations research. However, achieving accurate estimates often requires extensive online interaction with the environment, which can be costly or impractical in many real-world settings. In this paper, we develop a framework that improves the sample efficiency of online Monte Carlo estimators while preserving unbiasedness. We first derive a closed-form optimal behavior policy that minimizes estimator variance under unbiasedness constraints. We then propose practical algorithms for learning the proposed behavior policy from previously collected offline data, enabling improved online evaluation without requiring estimation of the environment transition model. We provide theoretical analysis that quantifies the resulting variance reduction and analyzes the impact of approximation errors. Empirical studies across diverse environments demonstrate substantial improvements in online sample efficiency compared with standard on-policy Monte Carlo evaluation and existing baseline methods. Our results provide a unified framework for optimal behavior policy design in off-policy evaluation, with applications to reinforcement learning and operations research.

cs.LG↗

Inductive Feedback for Mixed-Policy Distillation

Verbal feedback can identify errors and prescribe corrections, providing rich supervision for language-model post-training even when reliable programmatic verifiers are unavailable. Such feedback, often generated by a capable model, can be used to condition the teacher in on-policy distillation, which trains the student to match the teacher's predictions on student-generated rollouts. However, this approach can transfer teacher preferences that the feedback did not motivate, while leaving much of the feedback's guidance unused. We find that both problems come from the standard on-policy distillation objective, specifically the divergence it minimizes and the distribution it uses as its target. Our proposed method addresses both limitations. First, to isolate the information conveyed by the feedback from the teacher's inherent preferences, we treat verbal feedback as evidence for or against the hypothesis that a particular token comes next at a given prefix. We then adopt a probabilistic confirmation framework which uniquely determines an ordering over the vocabulary based on the teacher's predictions before and after it receives feedback. Using a confirmation score consistent with this ordering, we construct a target distribution within a trust region of the student. Second, to learn from guidance that student rollouts can leave unused, we derive a simple shared-rollout estimator of a symmetric divergence between the student and target distributions over rollouts, reusing student and feedback-conditioned teacher rollouts in both directions through importance weighting. Empirical evaluations show that our method outperforms the common on-policy distillation recipe and a recent contrastive variant on knowledge-based and agentic benchmarks.

cs.LG↗

Downstream-Aware Context Selection for Online In-Context Reinforcement Learning

In-context reinforcement learning (ICRL) enables large language model agents to adapt to new environments using their interaction history without updating model parameters. However, repeatedly conditioning on growing histories can lead to substantial token cost. We propose a bounded-history context-management framework that predicts the task-dependent downstream effect of removing historical interactions to guide history selection and determine a decision-dependent context budget. Formally, our framework uses the full rolling history as a reference. The predictor evaluates removal effects, defines a deletion ordering, and applies a shared selection criterion to determine how much history to retain at each decision. We evaluate the method in closed-loop SUMO driving under held-out in-distribution, unseen-domain, and unseen-route settings, and in ScienceWorld under a continual ICRL protocol. Relative to a baseline using the full context, our method reduces total token usage by 25.7%, 25.8%, and 23.2% across the three driving settings while maintaining comparable closed-loop driving performance. In ScienceWorld, it reduces total token usage by 52.1% compared to full context and uses 30.2% and 37.8% fewer tokens than the Recent and Similarity baselines, respectively, while maintaining performance.

cs.LG↗

OR-Transformer: Scaling Real-Time Decision-Making to 1,000 Items

Modern supply chain operations can require coordinating replenishment across thousands of heterogeneous items under correlated stochastic demand, heterogeneous lead times, and shared fixed ordering costs, yielding observation spaces exceeding $10^4$ dimensions. At this scale, rolling-horizon stochastic mixed-integer linear programs (MILPs) become prohibitively slow, while standard reinforcement learning (RL) methods face increasingly challenging credit assignment in high-dimensional action spaces. We introduce OR-Transformer, a deep reinforcement learning framework for joint replenishment under stochastic demand, with an item-permutation-equivariant Transformer architecture and pathwise-gradient training through the inventory dynamics. Across problem sizes up to 1,024 inventory items, OR-Transformer increasingly outperforms learning-based and rolling-horizon MILP baselines as scale grows. It also reduces online decision-making time by over 4 million times relative to MILP solvers, enabling real-time, large-scale deep RL in supply chain operations.

cs.LG↗

Robust Data-Collection Policy Learning for Low-Variance Online Policy Evaluation

In reinforcement learning policy evaluation, classic on-policy methods often suffer from high variance when estimating policy performance. To mitigate this issue, behavior policy search has been proposed to learn data-collecting policies tailored to reduce online evaluation variance. However, these approaches do not account for uncertainties in the transition functions. In practice, simulator transitions often differ from the real world due to modeling errors or approximation limitations. As a result, behavior policies trained in simulation may still yield high variance when deployed in real environments, leading to costly reliance on real-world evaluation samples. In this work, we propose a double-loop gradient-based algorithm for learning behavior policies that are both efficient and robust to transition uncertainty. Theoretically, we derive novel transition-variance gradient expressions and establish global convergence guarantees for the algorithm. Numerically, we demonstrate that our method is less sensitive to transition perturbations than existing approaches, providing supportive evidence for its practical utility.

cs.LG↗

Towards Formalizing Reinforcement Learning Theory: A Robbins-Siegmund Approach

In this paper, we formalize the almost sure convergence of $Q$-learning and linear temporal difference (TD) learning with Markovian samples using the Lean 4 theorem prover based on the Mathlib library. $Q$-learning and linear TD are among the earliest and most influential reinforcement learning (RL) algorithms. The investigation of their convergence properties is not only a major research topic during the early development of the RL field but also receives significant attention nowadays. This paper formally verifies their almost sure convergence in a unified framework based on the Robbins-Siegmund theorem. The framework developed in this work can potentially be extended to convergence rates and other modes of convergence. This work thus makes an important step towards fully formalizing convergent RL results. The code is available at https://github.com/ShangtongZhang/rl-theory-in-lean.

cs.LG↗

Reward Machines for Signal Temporal Logic

Signal temporal logic (STL) provides a formal language for specifying real-time properties of real-valued observations, along with a quantitative robustness score for monitoring satisfaction. Control synthesis from STL specifications is of interest since manual controller design becomes infeasible as real-world systems grow in complexity. Moreover, many modern autonomous and AI-enabled systems lack accurate and complete system models, which makes optimization-based synthesis approaches unsuitable and motivates learning-based control. Prior work uses STL robustness scores as rewards in reinforcement learning (RL) to obtain control policies satisfying given specifications; however, robustness depends on execution history, leading to intractable state space expansion for general long-horizon specifications with arbitrarily nested temporal operators. This work introduces a novel automata-based approach that provides an efficient memory mechanism and associated Markovian rewards suitable for RL frameworks. Our approach constructs a timed alternating automaton from the given STL specifications, augments the state space with automaton locations and clock valuations, and derives rewards from the automaton acceptance condition. We empirically demonstrate that our approach learns policies that achieve higher robustness scores and satisfaction rates than those learned by existing approaches using robustness-based rewards.

cs.AI↗

Multi-agent DRL-based Lane Change Decision Model for Cooperative Platooning in Mixed Traffic

Connected automated vehicles (CAVs) possess the ability to communicate and coordinate with one another, enabling cooperative platooning that enhances both energy efficiency and traffic flow. However, during the initial stage of CAV deployment, the sparse distribution of CAVs among human-driven vehicles reduces the likelihood of forming effective cooperative platoons. To address this challenge, this study proposes a hybrid multi-agent lane change decision model aimed at increasing CAV participation in cooperative platooning and maximizing its associated benefits. The proposed model employs the QMIX framework, integrating traffic data processed through a convolutional neural network (CNN-QMIX). This architecture addresses a critical issue in dynamic traffic scenarios by enabling CAVs to make optimal decisions irrespective of the varying number of CAVs present in mixed traffic. Additionally, a trajectory planner and a model predictive controller are designed to ensure smooth and safe lane-change execution. The proposed model is trained and evaluated within a microsimulation environment under varying CAV market penetration rates. The results demonstrate that the proposed model efficiently manages fluctuating traffic agent numbers, significantly outperforming the baseline rule-based models. Notably, it enhances cooperative platooning rates up to 26.2\%, showcasing its potential to optimize CAV cooperation and traffic dynamics during the early stage of deployment.

cs.AI↗

Safe In-Context Reinforcement Learning

In-context reinforcement learning (ICRL) is an emerging RL paradigm where an agent, after pretraining, can adapt to out-of-distribution test tasks without any parameter updates, instead relying on an expanding context of interaction history. While ICRL has shown impressive generalization, safety during this adaptation process remains unexplored, limiting its applicability in real-world deployments where test-time behavior is expected to be safe. In this work, we propose SCARED: Safe Contextual Adaptive Reinforcement via Exact-penalty Dual, the first method that promotes safe adaptation of ICRL under the constrained Markov decision process framework. During the parameter-update-free adaptation process, our agent not only maximizes the reward but also keeps the accumulated cost within a user-specified safety budget. We also demonstrate that the agent actively reacts to the safety budget; with a higher safety budget, the agent behaves more aggressively, and with a lower safety budget the agent behaves more conservatively. Across challenging benchmarks, SCARED consistently enables safe and robust in-context adaptation, outperforming existing ICRL and safe meta-RL baselines.

cs.LG↗

Active Offline-to-Online Reinforcement Learning

Background: Offline reinforcement learning (RL) enables effective policies to be trained from large, previously collected datasets and subsequently improved through limited online interaction. This offline-to-online RL (O2O-RL) paradigm is particularly promising in nonstationary domains where interaction is costly or potentially hazardous. Standard O2O-RL pipelines train multiple candidate policies offline, evaluate them using off-policy or online evaluation, and then deploy and fine-tune the policy with the highest estimated value. However, as in offline pretraining, fine-tuning performance is highly sensitive to the choice of algorithm and hyperparameters, making it risky to commit to a single policy. Objectives: We study active policy selection for fine-tuning under a limited interaction budget in O2O-RL settings. To our knowledge, this is the first work to address this problem. Methods: We formulate the problem by identifying a fundamental trade-off between allocating online interactions to policy evaluation, which helps identify high-performing policies, and allocating them to fine-tuning, which improves policy performance. We then propose an approach that balances this trade-off by actively selecting policies for fine-tuning based on upper-confidence bounds on their future performance. These bounds are derived from locally linear performance forecasts fitted to observations obtained through online evaluation. Results: Across a diverse range of experiments, the proposed approach consistently outperforms existing O2O-RL baselines. Conclusions: Actively selecting and fine-tuning policies uses limited online interaction budgets more effectively than either committing to a single policy or dividing the budget equally among all policies. Our framework also advances offline RL toward practical deployment in real-world systems where online interaction is costly or risky.

cs.LG↗

Convergence of Two-Timescale Markovian Stochastic Approximations with Applications in Reinforcement Learning

This work studies the convergence of two-timescale stochastic approximations (SA), a class of iterative algorithms that update two sets of parameters in fast and slow timescales respectively. Notable examples of two-timescale SA in reinforcement learning (RL) include temporal difference learning with gradient correction (TDC) and actor-critic methods. Previously, the stability (i.e., boundedness) and convergence of two-timescale SA were only established under i.i.d. noise. This work instead establishes the stability and convergence of two-timescale SA under Markovian noise, a setup that is more realistic in RL. Notably, we do not need to use any projection operator and the noise does not need to live in a compact space. Our key technical novelty is to control the fast timescale parameter with the running max of the slow timescale parameter, instead of with the current slow timescale parameter, as most prior works do. As a key application, we establish the first almost sure convergence of TDC with eligibility traces under off-policy learning with linear function approximation.

cs.LG↗

Extensions of Robbins-Siegmund Theorem with Applications in Reinforcement Learning

The Robbins-Siegmund theorem establishes the convergence of stochastic processes that are almost supermartingales and is one of the most commonly used approaches for analyzing stochastic iterative algorithms in stochastic approximation and reinforcement learning (RL). However, its original form has a significant limitation as it requires the zero-order term to be summable. In many important RL applications, this summable condition, however, cannot be met. This limitation motivates us to extend the Robbins-Siegmund theorem for almost supermartingales where the zero-order term is not summable, but only square-summable. In particular, we introduce a novel and mild assumption on the increments of the stochastic processes. This together with the square-summable condition enables an almost sure convergence to a bounded set. Additionally, we further provide almost sure convergence rates, high probability concentration bounds, and $L^p$ convergence rates. We then apply the new results to stochastic approximation and RL. Notably, we obtain the first almost sure convergence rate, the first high probability concentration bound, and the first $L^p$ convergence rate for $Q$-learning with linear function approximation.

cs.LG↗

MathlibLemma: Folklore Lemma Generation and Benchmark for Formal Mathematics

While the ecosystem of Lean and Mathlib has enjoyed celebrated success in formal mathematical reasoning with the help of large language models (LLMs), the absence of many folklore lemmas in Mathlib remains a persistent barrier that limits Lean's usability as an everyday tool for mathematicians like \LaTeX{} or Maple. To address this, we introduce MathlibLemma, a modular LLM-based pipeline for automated folklore-lemma mining: the discovery, formalization, and proving of reusable intermediate facts that mathematicians often take for granted but that are not always present in formal libraries. At its core, MathlibLemma proactively mines the missing connective tissue of mathematics. The pipeline produces a verified library of folklore-style lemmas, including 1,506 Lean-checked proofs that pass a proof-bypass screen; a small curated pilot subset has also been merged into Mathlib, providing external evidence that selected outputs can meet expert library standards. Leveraging this pipeline, we further construct the MathlibLemma benchmark, a suite of 4,028 non-trivial type-checked Lean statements spanning a broad range of mathematical domains. By transforming the role of LLMs from passive consumers to active contributors, this work takes a step toward AI-assisted expansion of formal mathematical libraries.

cs.LO↗