arXiv subjects

Yang Guan

Publications and source records attributed to Yang Guan.

At least 19 recordsLinked to original sources

arXiv2026

NeuralParker: A Reinforcement Learning Planner for Irregular Parking Environments

Automated parking commonly assumes marked slots and short approach maneuvers. Delivery and service vehicles, however, may need to reach an operator-specified pose in an irregular bounded environment from a distant start. Existing learning-based parking planners often rely on local observations, which can restrict long-range route reasoning. To address this problem, we present NeuralParker, a reinforcement learning-based hybrid planner for arbitrary-pose parking. NeuralParker encodes full-environment obstacle and boundary geometry in a target-relative vertex representation, allowing the policy to retain route-defining context throughout the approach. It further couples a learned curvature--length arc policy with an in-loop terminal ensemble that selects from diverse cubic Hermite connections using a curvature-regularized cost. We also establish factorial and long-range route-choice benchmarks to evaluate planning success and trajectory quality. Experiments on these benchmarks show that NeuralParker achieves higher planning success and better overall trajectory quality than the evaluated baselines, while ablation studies support the benefits of the target-relative global representation and terminal ensemble. Finally, a real-vehicle evaluation confirms that the planner transfers effectively to real delivery-vehicle perception at a working parking site, planning successfully at low computational cost.

cs.RO↗

arXiv2026

On the Identifiability of Controlled World Models

World model serves as a promising tool to infer environment dynamics under high-dimensional observations and candidate actions. Recently, LeCun's JEPA provides a compelling framework for learning such models in representation space. Its action-conditioned extension plays a central role in visual control and latent-space planning, but leaves a fundamental question: can it recover the controlled dynamics from nonlinear observations? This paper presents a joint identifiability condition for controlled world models with Gaussian latent states, which consists of two coupled components: (1) representation identifiability and (2) transition identifiability. The former depends on the spectral separation property while the latter is related to non-degenerate variation of conditional action. We prove that when this condition holds, minimizing the LeJEPA-style predictive objective can recover both latent states and controlled dynamics in the sense of orthogonal transformation. We further prove that the upper bound of transition prediction error is inversely proportional to the spectral separation margin. We also characterize an attainable amplification of counterfactual prediction error that scales inversely with the weakest conditional action-excitation margin. The theoretical predictions are empirically supported across four nonlinear observation settings.

cs.LG↗

arXiv2026

FAST: A Framework for Aligned Sampling and Training in Parallel Reinforcement Learning for Autonomous Driving

Deep reinforcement learning is pivotal for closed-loop autonomous driving yet remains constrained by severe bottlenecks in sampling efficiency. Standard parallel sampling mitigates this but suffers from the straggler effect, where the premature termination of a single environment necessitates a synchronized batch re-initialization, leading to suboptimal sample utilization and prohibitive re-initialization latency. To address this, we propose FAST, a synchronous parallel framework tailored for closed-loop simulation. Specifically, FAST employs Dynamic Parallel Sampling Alignment (DPSA) to maintain vectorization synchronization by extending terminated episodes via virtual continuation, thereby decoupling the sampling loop from individual terminations. By dynamically triggering global truncation based on the termination rate of parallel clips, FAST effectively eliminates the bottleneck of premature resets without sacrificing data diversity. Furthermore, to strictly preserve theoretical consistency, we incorporate a Scaled Mask-Padding Optimization (SMPO) that leverages validity masking and adaptive loss normalization to nullify the bias from auxiliary padding data. Empirical evaluations demonstrate that FAST achieves at least a 1.78 times wall-clock speedup over the single-clip baseline while preserving statistical unbiasedness.

cs.LG↗

arXiv2026

Towards Physically Consistent 4D Scene Reconstruction for Closed-loop Autonomous Driving Simulation

High-fidelity street scene reconstruction is pivotal for end-to-end autonomous driving simulation, where novel-view synthesis (NVS) and time-varying information modeling are two fundamental capabilities to facilitate closed-loop training. However, existing 3DGS methods and their 4D extensions fail to simultaneously achieve both. To bridge this gap, we establish an information-geometric diagnostic framework, revealing that this limitation stems from a credit assignment dilemma between spatial and temporal parameters. Specifically, the deterministic coupling between viewpoint and time in single-source observation creates a low-rank structure that induces massive null-space ambiguity between static view-dependent and dynamic time-varying components. Temporal information overshadows spatial cues, causing the estimation variance of spatial parameters to diverge. To address this issue, we propose Orthogonal Projected Gradient (OPG), a hierarchical training method designed to restore spatial identifiability. OPG prioritizes the integrity of spatial representations by securing them in an initial stage, then restricts temporal updates to the spatial null space, enabling proactive credit assignment. While OPG isolates temporal updates algebraically, Temporal Regularization Strategy is proposed to further refine the temporal solution space by imposing a smoothness constraint based on the physical prior of consistent appearance evolution, ensuring that the reconstructed scene remains physically consistent in closed-loop simulation. Extensive experiments demonstrate that our method not only maintains stable NVS capabilities but also demonstrates superior performance in traditional observation-reproducing metrics, which indirectly reflect the capability of modeling temporal dynamics.

cs.CV↗

arXiv2026

STAPO: Stabilizing Reinforcement Learning for LLMs by Silencing Rare Spurious Tokens

Reinforcement Learning (RL) has significantly improved large language model reasoning, but existing RL fine-tuning methods rely heavily on heuristic techniques such as entropy regularization and reweighting to maintain stability. In practice, they often suffer from late-stage performance collapse, leading to degraded reasoning quality and unstable training. We identify a key factor behind this instability: a small fraction of tokens, termed spurious tokens (around 0.01%), which contribute little to the reasoning outcome but receive disproportionately amplified gradient updates due to inheriting the full sequence-level reward. We present a unified framework for evaluating token-level optimization impacts across spurious risk, gradient norms, and entropy changes. Building on the analysis of token characteristics that severely disrupt optimization, we propose the Silencing Spurious Tokens (S2T) mechanism to efficiently suppress their gradient perturbations. Incorporating this mechanism into a group-based objective, we propose Spurious-Token-Aware Policy Optimization (STAPO), which promotes stable and effective large-scale model refinement. Across six mathematical reasoning benchmarks using Qwen 1.7B, 8B, and 14B base models, STAPO consistently demonstrates superior entropy stability and achieves an average performance improvement of 11.49% ($\rho_{\mathrm{T}}$=1.0, top-p=1.0) and 3.73% ($\rho_{\mathrm{T}}$=0.7, top-p=0.9) over GRPO, 20-Entropy, and JustRL.

cs.CL↗

arXiv2024

VeraCT Scan: Retrieval-Augmented Fake News Detection with Justifiable Reasoning

The proliferation of fake news poses a significant threat not only by disseminating misleading information but also by undermining the very foundations of democracy. The recent advance of generative artificial intelligence has further exacerbated the challenge of distinguishing genuine news from fabricated stories. In response to this challenge, we introduce VeraCT Scan, a novel retrieval-augmented system for fake news detection. This system operates by extracting the core facts from a given piece of news and subsequently conducting an internet-wide search to identify corroborating or conflicting reports. Then sources' credibility is leveraged for information verification. Besides determining the veracity of news, we also provide transparent evidence and reasoning to support its conclusions, resulting in the interpretability and trust in the results. In addition to GPT-4 Turbo, Llama-2 13B is also fine-tuned for news content understanding, information verification, and reasoning. Both implementations have demonstrated state-of-the-art accuracy in the realm of fake news detection.

cs.CL↗

arXiv2022

Integrated Decision and Control for High-Level Automated Vehicles by Mixed Policy Gradient and Its Experiment Verification

Self-evolution is indispensable to realize full autonomous driving. This paper presents a self-evolving decision-making system based on the Integrated Decision and Control (IDC), an advanced framework built on reinforcement learning (RL). First, an RL algorithm called constrained mixed policy gradient (CMPG) is proposed to consistently upgrade the driving policy of the IDC. It adapts the MPG under the penalty method so that it can solve constrained optimization problems using both the data and model. Second, an attention-based encoding (ABE) method is designed to tackle the state representation issue. It introduces an embedding network for feature extraction and a weighting network for feature fusion, fulfilling order-insensitive encoding and importance distinguishing of road users. Finally, by fusing CMPG and ABE, we develop the first data-driven decision and control system under the IDC architecture, and deploy the system on a fully-functional self-driving vehicle running in daily operation. Experiment results show that boosting by data, the system can achieve better driving ability over model-based methods. It also demonstrates safe, efficient and smart driving behavior in various complex scenes at a signalized intersection with real mixed traffic flow.

cs.RO↗

arXiv2021

Encoding Distributional Soft Actor-Critic for Autonomous Driving in Multi-lane Scenarios

In this paper, we propose a new reinforcement learning (RL) algorithm, called encoding distributional soft actor-critic (E-DSAC), for decision-making in autonomous driving. Unlike existing RL-based decision-making methods, E-DSAC is suitable for situations where the number of surrounding vehicles is variable and eliminates the requirement for manually pre-designed sorting rules, resulting in higher policy performance and generality. We first develop an encoding distributional policy iteration (DPI) framework by embedding a permutation invariant module, which employs a feature neural network (NN) to encode the indicators of each vehicle, in the distributional RL framework. The proposed DPI framework is proved to exhibit important properties in terms of convergence and global optimality. Next, based on the developed encoding DPI framework, we propose the E-DSAC algorithm by adding the gradient-based update rule of the feature NN to the policy evaluation process of the DSAC algorithm. Then, the multi-lane driving task and the corresponding reward function are designed to verify the effectiveness of the proposed algorithm. Results show that the policy learned by E-DSAC can realize efficient, smooth, and relatively safe autonomous driving in the designed scenario. And the final policy performance learned by E-DSAC is about three times that of DSAC. Furthermore, its effectiveness has also been verified in real vehicle experiments.

cs.RO↗

arXiv2021

Integrated Decision and Control at Multi-Lane Intersections with Mixed Traffic Flow

Autonomous driving at intersections is one of the most complicated and accident-prone traffic scenarios, especially with mixed traffic participants such as vehicles, bicycles and pedestrians. The driving policy should make safe decisions to handle the dynamic traffic conditions and meet the requirements of on-board computation. However, most of the current researches focuses on simplified intersections considering only the surrounding vehicles and idealized traffic lights. This paper improves the integrated decision and control framework and develops a learning-based algorithm to deal with complex intersections with mixed traffic flows, which can not only take account of realistic characteristics of traffic lights, but also learn a safe policy under different safety constraints. We first consider different velocity models for green and red lights in the training process and use a finite state machine to handle different modes of light transformation. Then we design different types of distance constraints for vehicles, traffic lights, pedestrians, bicycles respectively and formulize the constrained optimal control problems (OCPs) to be optimized. Finally, reinforcement learning (RL) with value and policy networks is adopted to solve the series of OCPs. In order to verify the safety and efficiency of the proposed method, we design a multi-lane intersection with the existence of large-scale mixed traffic participants and set practical traffic light phases. The simulation results indicate that the trained decision and control policy can well balance safety and tracking performance. Compared with model predictive control (MPC), the computational time is three orders of magnitude lower.

cs.LG↗

arXiv2021

Model-based Chance-Constrained Reinforcement Learning via Separated Proportional-Integral Lagrangian

Safety is essential for reinforcement learning (RL) applied in the real world. Adding chance constraints (or probabilistic constraints) is a suitable way to enhance RL safety under uncertainty. Existing chance-constrained RL methods like the penalty methods and the Lagrangian methods either exhibit periodic oscillations or learn an over-conservative or unsafe policy. In this paper, we address these shortcomings by proposing a separated proportional-integral Lagrangian (SPIL) algorithm. We first review the constrained policy optimization process from a feedback control perspective, which regards the penalty weight as the control input and the safe probability as the control output. Based on this, the penalty method is formulated as a proportional controller, and the Lagrangian method is formulated as an integral controller. We then unify them and present a proportional-integral Lagrangian method to get both their merits, with an integral separation technique to limit the integral value in a reasonable range. To accelerate training, the gradient of safe probability is computed in a model-based manner. We demonstrate our method can reduce the oscillations and conservatism of RL policy in a car-following simulation. To prove its practicality, we also apply our method to a real-world mobile robot navigation task, where our robot successfully avoids a moving obstacle with highly uncertain or even aggressive behaviors.

cs.LG↗

arXiv2021

Feasible Actor-Critic: Constrained Reinforcement Learning for Ensuring Statewise Safety

The safety constraints commonly used by existing safe reinforcement learning (RL) methods are defined only on expectation of initial states, but allow each certain state to be unsafe, which is unsatisfying for real-world safety-critical tasks. In this paper, we introduce the feasible actor-critic (FAC) algorithm, which is the first model-free constrained RL method that considers statewise safety, e.g, safety for each initial state. We claim that some states are inherently unsafe no matter what policy we choose, while for other states there exist policies ensuring safety, where we say such states and policies are feasible. By constructing a statewise Lagrange function available on RL sampling and adopting an additional neural network to approximate the statewise Lagrange multiplier, we manage to obtain the optimal feasible policy which ensures safety for each feasible state and the safest possible policy for infeasible states. Furthermore, the trained multiplier net can indicate whether a given state is feasible or not through the statewise complementary slackness condition. We provide theoretical guarantees that FAC outperforms previous expectation-based constrained RL methods in terms of both constraint satisfaction and reward optimization. Experimental results on both robot locomotive tasks and safe exploration tasks verify the safety enhancement and feasibility interpretation of the proposed method.

cs.LG↗

arXiv2021

Distributional Soft Actor-Critic: Off-Policy Reinforcement Learning for Addressing Value Estimation Errors

In reinforcement learning (RL), function approximation errors are known to easily lead to the Q-value overestimations, thus greatly reducing policy performance. This paper presents a distributional soft actor-critic (DSAC) algorithm, which is an off-policy RL method for continuous control setting, to improve the policy performance by mitigating Q-value overestimations. We first discover in theory that learning a distribution function of state-action returns can effectively mitigate Q-value overestimations because it is capable of adaptively adjusting the update stepsize of the Q-value function. Then, a distributional soft policy iteration (DSPI) framework is developed by embedding the return distribution function into maximum entropy RL. Finally, we present a deep off-policy actor-critic variant of DSPI, called DSAC, which directly learns a continuous return distribution by keeping the variance of the state-action returns within a reasonable range to address exploding and vanishing gradient problems. We evaluate DSAC on the suite of MuJoCo continuous control tasks, achieving the state-of-the-art performance.

cs.LG↗

arXiv2021

Direct and indirect reinforcement learning

Reinforcement learning (RL) algorithms have been successfully applied to a range of challenging sequential decision making and control tasks. In this paper, we classify RL into direct and indirect RL according to how they seek the optimal policy of the Markov decision process problem. The former solves the optimal policy by directly maximizing an objective function using gradient descent methods, in which the objective function is usually the expectation of accumulative future rewards. The latter indirectly finds the optimal policy by solving the Bellman equation, which is the sufficient and necessary condition from Bellman's principle of optimality. We study policy gradient forms of direct and indirect RL and show that both of them can derive the actor-critic architecture and can be unified into a policy gradient with the approximate value function and the stationary state distribution, revealing the equivalence of direct and indirect RL. We employ a Gridworld task to verify the influence of different forms of policy gradient, suggesting their differences and relationships experimentally. Finally, we classify current mainstream RL algorithms using the direct and indirect taxonomy, together with other ones including value-based and policy-based, model-based and model-free.

cs.LG↗

arXiv2021

Integrated Decision and Control: Towards Interpretable and Computationally Efficient Driving Intelligence

Decision and control are core functionalities of high-level automated vehicles. Current mainstream methods, such as functionality decomposition and end-to-end reinforcement learning (RL), either suffer high time complexity or poor interpretability and adaptability on real-world autonomous driving tasks. In this paper, we present an interpretable and computationally efficient framework called integrated decision and control (IDC) for automated vehicles, which decomposes the driving task into static path planning and dynamic optimal tracking that are structured hierarchically. First, the static path planning generates several candidate paths only considering static traffic elements. Then, the dynamic optimal tracking is designed to track the optimal path while considering the dynamic obstacles. To that end, we formulate a constrained optimal control problem (OCP) for each candidate path, optimize them separately and follow the one with the best tracking performance. To unload the heavy online computation, we propose a model-based reinforcement learning (RL) algorithm that can be served as an approximate constrained OCP solver. Specifically, the OCPs for all paths are considered together to construct a single complete RL problem and then solved offline in the form of value and policy networks, for real-time online path selecting and tracking respectively. We verify our framework in both simulations and the real world. Results show that compared with baseline methods IDC has an order of magnitude higher online computing efficiency, as well as better driving performance including traffic efficiency and safety. In addition, it yields great interpretability and adaptability among different driving tasks. The effectiveness of the proposed method is also demonstrated in real road tests with complicated traffic conditions.

cs.LG↗

arXiv2021

Model-Based Actor-Critic with Chance Constraint for Stochastic System

Safety is essential for reinforcement learning (RL) applied in real-world situations. Chance constraints are suitable to represent the safety requirements in stochastic systems. Previous chance-constrained RL methods usually have a low convergence rate, or only learn a conservative policy. In this paper, we propose a model-based chance constrained actor-critic (CCAC) algorithm which can efficiently learn a safe and non-conservative policy. Different from existing methods that optimize a conservative lower bound, CCAC directly solves the original chance constrained problems, where the objective function and safe probability is simultaneously optimized with adaptive weights. In order to improve the convergence rate, CCAC utilizes the gradient of dynamic model to accelerate policy optimization. The effectiveness of CCAC is demonstrated by a stochastic car-following task. Experiments indicate that compared with previous RL methods, CCAC improves the performance while guaranteeing safety, with a five times faster convergence rate. It also has 100 times higher online computation efficiency than traditional safety techniques such as stochastic model predictive control.

cs.LG↗

arXiv2021

Centralized Cooperation for Connected and Automated Vehicles at Intersections by Proximal Policy Optimization

Connected vehicles will change the modes of future transportation management and organization, especially at an intersection without traffic light. Centralized coordination methods globally coordinate vehicles approaching the intersection from all sections by considering their states altogether. However, they need substantial computation resources since they own a centralized controller to optimize the trajectories for all approaching vehicles in real-time. In this paper, we propose a centralized coordination scheme of automated vehicles at an intersection without traffic signals using reinforcement learning (RL) to address low computation efficiency suffered by current centralized coordination methods. We first propose an RL training algorithm, model accelerated proximal policy optimization (MA-PPO), which incorporates a prior model into proximal policy optimization (PPO) algorithm to accelerate the learning process in terms of sample efficiency. Then we present the design of state, action and reward to formulate centralized coordination as an RL problem. Finally, we train a coordinate policy in a simulation setting and compare computing time and traffic efficiency with a coordination scheme based on model predictive control (MPC) method. Results show that our method spends only 1/400 of the computing time of MPC and increase the efficiency of the intersection by 4.5 times.

cs.RO↗

arXiv2021

Approximate Optimal Filter for Linear Gaussian Time-invariant Systems

State estimation is critical to control systems, especially when the states cannot be directly measured. This paper presents an approximate optimal filter, which enables to use policy iteration technique to obtain the steady-state gain in linear Gaussian time-invariant systems. This design transforms the optimal filtering problem with minimum mean square error into an optimal control problem, called Approximate Optimal Filtering (AOF) problem. The equivalence holds given certain conditions about initial state distributions and policy formats, in which the system state is the estimation error, control input is the filter gain, and control objective function is the accumulated estimation error. We present a policy iteration algorithm to solve the AOF problem in steady-state. A classic vehicle state estimation problem finally evaluates the approximate filter. The results show that the policy converges to the steady-state Kalman gain, and its accuracy is within 2 %.

eess.SY↗

arXiv2021

Decision-Making under On-Ramp merge Scenarios by Distributional Soft Actor-Critic Algorithm

Merging into the highway from the on-ramp is an essential scenario for automated driving. The decision-making under the scenario needs to balance the safety and efficiency performance to optimize a long-term objective, which is challenging due to the dynamic, stochastic, and adversarial characteristics. The Rule-based methods often lead to conservative driving on this task while the learning-based methods have difficulties meeting the safety requirements. In this paper, we propose an RL-based end-to-end decision-making method under a framework of offline training and online correction, called the Shielded Distributional Soft Actor-critic (SDSAC). The SDSAC adopts the policy evaluation with safety consideration and a safety shield parameterized with the barrier function in its offline training and online correction, respectively. These two measures support each other for better safety while not damaging the efficiency performance severely. We verify the SDSAC on an on-ramp merge scenario in simulation. The results show that the SDSAC has the best safety performance compared to baseline algorithms and achieves efficient driving simultaneously.

cs.RO↗