arXiv subjects

Sicun Gao

Publications and source records attributed to Sicun Gao.

At least 19 recordsLinked to original sources

arXiv2026

RN-D: Discretized Categorical Actors for On-Policy Reinforcement Learning

On-policy Reinforcement Learning (RL) remains a dominant paradigm for continuous control, yet standard implementations rely on Gaussian actors and relatively shallow MLP policies, often leading to brittle optimization when gradients are noisy, and policy updates must be conservative. In this paper, we revisit actor policy representation as a first-class design choice for on-policy RL. We study discretized categorical actors, which represent each action dimension as a distribution over discrete bins and induce a policy objective analogous to classification cross-entropy loss. Building on architectural advances from supervised learning, we further pair discretized categorical actors with regularized networks, yielding RN-D. Across diverse continuous-control benchmarks, we show that simply replacing the standard Gaussian actor with our proposed actor substantially improves performance, achieving state-of-the-art results within on-policy RL. We release our code at https://github.com/alwaysbyx/RND-RL.

cs.LG↗

arXiv2026

Sensitivity Shaping for Latent Modeling

Generative dynamics models enable planning in challenging robotic systems, but safe deployment requires reliably detecting policy-induced out-of-distribution (OOD) transitions. Existing methods typically treat the learned dynamics as fixed and attach post hoc support surrogates. We show that these surrogates can fail when the dynamics are locally insensitive to critical action choices: unsupported control actions may produce latent predictions that resemble demonstrated transitions, suppressing OOD signals despite large true predictive errors. To address this, we introduce support-conditioned control-sensitivity regularization, which promotes sensitive local response to control input changes in learned dynamics in high-support training regions. This preserves control-induced variation while limiting unstable extrapolation due to weak empirical support. Experiments in vision-based obstacle avoidance, manipulation, and real-robot navigation show improved OOD detection and safer closed-loop planning.

cs.RO↗

arXiv2026

Learning Quadruped Walking from Seconds of Demonstration

Quadruped locomotion provides a natural setting for understanding when model-free learning can outperform model-based control design, by exploiting data patterns to bypass the difficulty of optimizing over discrete contacts and the combinatorial explosion of mode changes. We give a principled analysis of why imitation learning with quadrupeds can be inherently effective in a small data regime, based on the structure of its limit cycles, Poincaré return maps, and local numerical properties of neural networks. The understanding motivates a new imitation learning method that regulates the alignment between variations in a latent space and those over the output actions. Hardware experiments confirm that a few seconds of demonstration is sufficient to train various locomotion policies from scratch entirely offline with reasonable robustness.

cs.LG↗

arXiv2026

Learning to Nudge: A Scalable Barrier Function Framework for Safe Robot Interaction in Dense Clutter

Robots operating in everyday environments must navigate and manipulate within densely cluttered spaces, where physical contact with surrounding objects is unavoidable. Traditional safety frameworks treat contact as unsafe, restricting robots to collision avoidance and limiting their ability to function in dense, everyday settings. As the number of objects grows, model-based approaches for safe manipulation become computationally intractable; meanwhile, learned methods typically tie safety to the task at hand, making them hard to transfer to new tasks without retraining. In this work we introduce Dense Contact Barrier Functions(DCBF). Our approach bypasses the computational complexity of explicitly modeling multi-object dynamics by instead learning a composable, object-centric function that implicitly captures the safety constraints arising from physical interactions. Trained offline on interactions with a few objects, the learned DCBFcomposes across arbitrary object sets at runtime, producing a single global safety filter that scales linearly and transfers across tasks without retraining. We validate our approach through simulated experiments in dense clutter, demonstrating its ability to enable collision-free navigation and safe, contact-rich interaction in suitable settings.

cs.RO↗

arXiv2025

May I have your Attention? Breaking Fine-Tuning based Prompt Injection Defenses using Architecture-Aware Attacks

A popular class of defenses against prompt injection attacks on large language models (LLMs) relies on fine-tuning to separate instructions and data, so that the LLM does not follow instructions that might be present with data. We evaluate the robustness of this approach in the whitebox setting by constructing strong optimization-based attacks, and show that the defenses do not provide the claimed security properties. Specifically, we construct a novel attention-based attack algorithm for textual LLMs and apply it to three recent whitebox defenses SecAlign (CCS 2025), SecAlign++, and StruQ (USENIX Security 2025), showing attacks with success rates of up to \textbf{85-95\%} on unseen prompts with modest increase in attacker budget in terms of tokens. Our findings make fundamental progress towards understanding the robustness of prompt injection defenses in the whitebox setting. We release our code and attacks at https://github.com/nishitvp/better_opts_attacks

cs.CR↗

arXiv2025

Controllable Motion Generation via Diffusion Modal Coupling

Diffusion models have recently gained significant attention in robotics due to their ability to generate multi-modal distributions of system states and behaviors. However, a key challenge remains: ensuring precise control over the generated outcomes without compromising realism. This is crucial for applications such as motion planning or trajectory forecasting, where adherence to physical constraints and task-specific objectives is essential. We propose a novel framework that enhances controllability in diffusion models by leveraging multi-modal prior distributions and enforcing strong modal coupling. This allows us to initiate the denoising process directly from distinct prior modes that correspond to different possible system behaviors, ensuring sampling to align with the training distribution. We evaluate our approach on motion prediction using the Waymo dataset and multi-task control in Maze2D environments. Experimental results show that our framework outperforms both guidance-based techniques and conditioned models with unimodal priors, achieving superior fidelity, diversity, and controllability, even in the absence of explicit conditioning. Overall, our approach provides a more reliable and scalable solution for controllable motion generation in robotics.

cs.RO↗

arXiv2025

Regulating Algorithmic Management: A Multi-Stakeholder Study of Challenges in Aligning Software and the Law for Workplace Scheduling

Algorithmic management (AM)'s impact on worker well-being has led to calls for regulation. However, little is known about the effectiveness and challenges in real-world AM regulation across the regulatory process -- rule operationalization, software use, and enforcement. Our multi-stakeholder study addresses this gap within workplace scheduling, one of the few AM domains with implemented regulations. We interviewed 38 stakeholders across the regulatory process: regulators, defense attorneys, worker advocates, managers, and workers. Our findings suggest that the efficacy of AM regulation is influenced by: (i) institutional constraints that challenge efforts to encode law into AM software, (ii) on-the-ground use of AM software that shapes its ability to facilitate compliance, (iii) mismatches between software and regulatory contexts that hinder enforcement, and (iv) unique concerns that software introduces when used to regulate AM. These findings underscore the importance of a sociotechnical approach to AM regulation, which considers organizational and collaborative contexts alongside the inherent attributes of software. We offer future research directions and implications for technology policy and design.

cs.CY↗

arXiv2025

Sequence Modeling for Time-Optimal Quadrotor Trajectory Optimization with Sampling-based Robustness Analysis

Time-optimal trajectories drive quadrotors to their dynamic limits, but computing such trajectories involves solving non-convex problems via iterative nonlinear optimization, making them prohibitively costly for real-time applications. In this work, we investigate learning-based models that imitate a model-based time-optimal trajectory planner to accelerate trajectory generation. Given a dataset of collision-free geometric paths, we show that modeling architectures can effectively learn the patterns underlying time-optimal trajectories. We introduce a quantitative framework to analyze local analytic properties of the learned models, and link them to the Backward Reachable Tube of the geometric tracking controller. To enhance robustness, we propose a data augmentation scheme that applies random perturbations to the input paths. Compared to classical planners, our method achieves substantial speedups, and we validate its real-time feasibility on a hardware quadrotor platform. Experiments demonstrate that the learned models generalize to previously unseen path lengths. The code for our approach can be found here: https://github.com/maokat12/lbTOPPQuad

cs.RO↗

arXiv2025

When Maximum Entropy Misleads Policy Optimization

The Maximum Entropy Reinforcement Learning (MaxEnt RL) framework is a leading approach for achieving efficient learning and robust performance across many RL tasks. However, MaxEnt methods have also been shown to struggle with performance-critical control problems in practice, where non-MaxEnt algorithms can successfully learn. In this work, we analyze how the trade-off between robustness and optimality affects the performance of MaxEnt algorithms in complex control tasks: while entropy maximization enhances exploration and robustness, it can also mislead policy optimization, leading to failure in tasks that require precise, low-entropy policies. Through experiments on a variety of control problems, we concretely demonstrate this misleading effect. Our analysis leads to better understanding of how to balance reward design and entropy maximization in challenging control problems.

cs.LG↗

arXiv2025

Improving Compositional Generation with Diffusion Models Using Lift Scores

We introduce a novel resampling criterion using lift scores, for improving compositional generation in diffusion models. By leveraging the lift scores, we evaluate whether generated samples align with each single condition and then compose the results to determine whether the composed prompt is satisfied. Our key insight is that lift scores can be efficiently approximated using only the original diffusion model, requiring no additional training or external modules. We develop an optimized variant that achieves relatively lower computational overhead during inference while maintaining effectiveness. Through extensive experiments, we demonstrate that lift scores significantly improved the condition alignment for compositional generation across 2D synthetic data, CLEVR position tasks, and text-to-image synthesis. Our code is available at http://rainorangelemon.github.io/complift.

cs.LG↗

arXiv2025

Improving Value Estimation Critically Enhances Vanilla Policy Gradient

Modern policy gradient algorithms, such as TRPO and PPO, outperform vanilla policy gradient in many RL tasks. Questioning the common belief that enforcing approximate trust regions leads to steady policy improvement in practice, we show that the more critical factor is the enhanced value estimation accuracy from more value update steps in each iteration. To demonstrate, we show that by simply increasing the number of value update steps per iteration, vanilla policy gradient itself can achieve performance comparable to or better than PPO in all the standard continuous control benchmark environments. Importantly, this simple change to vanilla policy gradient is significantly more robust to hyperparameter choices, opening up the possibility that RL algorithms may still become more effective and easier to use.

cs.LG↗

arXiv2025

Safe Human Robot Navigation in Warehouse Scenario

The integration of autonomous mobile robots (AMRs) in industrial environments, particularly warehouses, has revolutionized logistics and operational efficiency. However, ensuring the safety of human workers in dynamic, shared spaces remains a critical challenge. This work proposes a novel methodology that leverages control barrier functions (CBFs) to enhance safety in warehouse navigation. By integrating learning-based CBFs with the Open Robotics Middleware Framework (OpenRMF), the system achieves adaptive and safety-enhanced controls in multi-robot, multi-agent scenarios. Experiments conducted using various robot platforms demonstrate the efficacy of the proposed approach in avoiding static and dynamic obstacles, including human pedestrians. Our experiments evaluate different scenarios in which the number of robots, robot platforms, speed, and number of obstacles are varied, from which we achieve promising performance.

cs.RO↗

arXiv2025

Estimating Control Barriers from Offline Data

Learning-based methods for constructing control barrier functions (CBFs) are gaining popularity for ensuring safe robot control. A major limitation of existing methods is their reliance on extensive sampling over the state space or online system interaction in simulation. In this work we propose a novel framework for learning neural CBFs through a fixed, sparsely-labeled dataset collected prior to training. Our approach introduces new annotation techniques based on out-of-distribution analysis, enabling efficient knowledge propagation from the limited labeled data to the unlabeled data. We also eliminate the dependency on a high-performance expert controller, and allow multiple sub-optimal policies or even manual control during data collection. We evaluate the proposed method on real-world platforms. With limited amount of offline data, it achieves state-of-the-art performance for dynamic obstacle avoidance, demonstrating statistically safer and less conservative maneuvers compared to existing methods.

eess.SY↗

arXiv2024

SEEV: Synthesis with Efficient Exact Verification for ReLU Neural Barrier Functions

Neural Control Barrier Functions (NCBFs) have shown significant promise in enforcing safety constraints on nonlinear autonomous systems. State-of-the-art exact approaches to verifying safety of NCBF-based controllers exploit the piecewise-linear structure of ReLU neural networks, however, such approaches still rely on enumerating all of the activation regions of the network near the safety boundary, thus incurring high computation cost. In this paper, we propose a framework for Synthesis with Efficient Exact Verification (SEEV). Our framework consists of two components, namely (i) an NCBF synthesis algorithm that introduces a novel regularizer to reduce the number of activation regions at the safety boundary, and (ii) a verification algorithm that exploits tight over-approximations of the safety conditions to reduce the cost of verifying each piecewise-linear segment. Our simulations show that SEEV significantly improves verification efficiency while maintaining the CBF quality across various benchmark systems and neural network structures. Our code is available at https://github.com/HongchaoZhang-HZ/SEEV.

eess.SY↗

arXiv2024

Patching Approximately Safe Value Functions Leveraging Local Hamilton-Jacobi Reachability Analysis

Safe value functions, such as control barrier functions, characterize a safe set and synthesize a safety filter, overriding unsafe actions, for a dynamic system. While function approximators like neural networks can synthesize approximately safe value functions, they typically lack formal guarantees. In this paper, we propose a local dynamic programming-based approach to "patch" approximately safe value functions to obtain a safe value function. This algorithm, HJ-Patch, produces a novel value function that provides formal safety guarantees, yet retains the global structure of the initial value function. HJ-Patch modifies an approximately safe value function at states that are both (i) near the safety boundary and (ii) may violate safety. We iteratively update both this set of "active" states and the value function until convergence. This approach bridges the gap between value function approximation methods and formal safety through Hamilton-Jacobi (HJ) reachability, offering a framework for integrating various safety methods. We provide simulation results on analytic and learned examples, demonstrating HJ-Patch reduces the computational complexity by 2 orders of magnitude with respect to standard HJ reachability. Additionally, we demonstrate the perils of using approximately safe value functions directly and showcase improved safety using HJ-Patch.

cs.RO↗

arXiv2024

Hamilton-Jacobi Reachability in Reinforcement Learning: A Survey

Recent literature has proposed approaches that learn control policies with high performance while maintaining safety guarantees. Synthesizing Hamilton-Jacobi (HJ) reachable sets has become an effective tool for verifying safety and supervising the training of reinforcement learning-based control policies for complex, high-dimensional systems. Previously, HJ reachability was restricted to verifying low-dimensional dynamical systems primarily because the computational complexity of the dynamic programming approach it relied on grows exponentially with the number of system states. In recent years, a litany of proposed methods addresses this limitation by computing the reachability value function simultaneously with learning control policies to scale HJ reachability analysis while still maintaining a reliable estimate of the true reachable set. These HJ reachability approximations are used to improve the safety, and even reward performance, of learned control policies and can solve challenging tasks such as those with dynamic obstacles and/or with lidar-based or vision-based observations. In this survey paper, we review the recent developments in the field of HJ reachability estimation in reinforcement learning that would provide a foundational basis for further research into reliability in high-dimensional systems.

eess.SY↗

arXiv2024

Breaking the Barrier: Enhanced Utility and Robustness in Smoothed DRL Agents

Robustness remains a paramount concern in deep reinforcement learning (DRL), with randomized smoothing emerging as a key technique for enhancing this attribute. However, a notable gap exists in the performance of current smoothed DRL agents, often characterized by significantly low clean rewards and weak robustness. In response to this challenge, our study introduces innovative algorithms aimed at training effective smoothed robust DRL agents. We propose S-DQN and S-PPO, novel approaches that demonstrate remarkable improvements in clean rewards, empirical robustness, and robustness guarantee across standard RL benchmarks. Notably, our S-DQN and S-PPO agents not only significantly outperform existing smoothed agents by an average factor of $2.16\times$ under the strongest attack, but also surpass previous robustly-trained agents by an average factor of $2.13\times$. This represents a significant leap forward in the field. Furthermore, we introduce Smoothed Attack, which is $1.89\times$ more effective in decreasing the rewards of smoothed agents than existing adversarial attacks.

cs.LG↗

arXiv2024

Understanding the Difficulty of Solving Cauchy Problems with PINNs

Physics-Informed Neural Networks (PINNs) have gained popularity in scientific computing in recent years. However, they often fail to achieve the same level of accuracy as classical methods in solving differential equations. In this paper, we identify two sources of this issue in the case of Cauchy problems: the use of $L^2$ residuals as objective functions and the approximation gap of neural networks. We show that minimizing the sum of $L^2$ residual and initial condition error is not sufficient to guarantee the true solution, as this loss function does not capture the underlying dynamics. Additionally, neural networks are not capable of capturing singularities in the solutions due to the non-compactness of their image sets. This, in turn, influences the existence of global minima and the regularity of the network. We demonstrate that when the global minimum does not exist, machine precision becomes the predominant source of achievable error in practice. We also present numerical experiments in support of our theoretical claims.

cs.LG↗