Yanan Sui

Jieshi He, Puzhe Li, Yanan Sui et al.

Understanding how cortical activity represents natural whole-body behaviors in primates remains challenging. Limited by the diversity of movements and inaccessibility of large-scale neural representation of whole-body kinematics, previous motor decoding studies focused on constrained tasks and limited limb movements. Here, we present a neural-behavioral recording and modeling framework for freely moving monkeys, combining large-scale epidural cortical signals from distributed sensory- and motor-related areas with synchronized multi-view motion capture through a custom-made data collection platform. We reconstructed whole-body monkey kinematics and learned a compact behavior prior using an autoregressive encoder-decoder model. Conditioned on neural signals, the model decoded accurate and realistic whole-body movement without explicit physical constraints. Our results provide a novel proof-of-concept approach for decoding natural whole-body movements in primates using large-scale intracranial neural activity.

Cheryl Wang, Chun Kwang Tan, Balint K. Hodossy et al.

Athletic performance represents the pinnacle of human motor intelligence, demanding rapid choices, precise control, agility, and coordinated physical execution. Replicating this seamless combination of capabilities remains elusive in current artificial intelligence and robotic systems. Concurrently, understanding the biological mastery of these movements is hindered because complex muscle coordination is rarely measured in vivo due to the limitations of physical equipment. To bridge this fundamental gap in understanding, MyoChallenge at NeurIPS 2025 established a pioneering benchmark for motor control intelligence in sports, leveraging high-fidelity musculoskeletal models within physics simulation combined with machine learning-driven algorithms. The competition introduces two distinct tracks emphasizing either upper or lower limbs control: a table tennis rally task utilizing a biomechanic upper limb composed of an arm with a hand and a trunk; and a soccer penalty kick using a biomechanic model of legs and a trunk. Marking the fourth iteration of the MyoChallenge series, this event attracted almost 70 teams and over 560 submissions globally, uniting a diverse community ranging from physicians and neuroscientists to machine learning experts. The competition facilitated the development of several state-of-the-art control algorithms for a musculoskeletal system capable of sports agility, leveraging techniques such as physics-based motion planners, on-policy behaviour cloning, hierarchical planning, and muscle synergies. By integrating standardized tasks and physiologically realistic models into the open-source framework of MyoSuite, MyoChallenge'25 serves as a reproducible and reusable testbed to accelerate interdisciplinary research across machine learning, biomechanics, sports science, and neuroscience. Project page: https://www.myosuite.org//myochallenge/myochallenge-2025.

Chen Gong, Yue Chen, Yanan Sui et al.

The detection of human sleep stages is widely used in the diagnosis and intervention of neurological and psychiatric diseases. Some patients with deep brain stimulator implanted could have their neural activities recorded from the deep brain. Sleep stage classification based on deep brain recording has great potential to provide more precise treatment for patients. The accuracy and generalizability of existing sleep stage classifiers based on local field potentials are still limited. We proposed an applicable cross-modal transfer learning method for sleep stage classification with implanted devices. This end-to-end deep learning model contained cross-modal self-supervised feature representation, self-attention, and classification framework. We tested the model with deep brain recording data from 12 patients with Parkinson's disease. The best total accuracy reached 83.2% for sleep stage classification. Results showed speech self-supervised features catch the conversion pattern of sleep stages effectively. We provide a new method on transfer learning from acoustic signals to local field potentials. This method supports an effective solution for the insufficient scale of clinical data. This sleep stage classification model could be adapted to chronic and continuous monitor sleep for Parkinson's patients in daily life, and potentially utilized for more precise treatment in deep brain-machine interfaces, such as closed-loop deep brain stimulation.

Kaibo He, Chenhui Zuo, Chengtian Ma et al.

Learning an effective policy to control high-dimensional, overactuated systems is a significant challenge for deep reinforcement learning algorithms. Such control scenarios are often observed in the neural control of vertebrate musculoskeletal systems. The study of these control mechanisms will provide insights into the control of high-dimensional, overactuated systems. The coordination of actuators, known as muscle synergies in neuromechanics, is considered a presumptive mechanism that simplifies the generation of motor commands. The dynamical structure of a system is the basis of its function, allowing us to derive a synergistic representation of actuators. Motivated by this theory, we propose the Dynamical Synergistic Representation (DynSyn) algorithm. DynSyn aims to generate synergistic representations from dynamical structures and perform task-specific, state-dependent adaptation to the representations to improve motor control. We demonstrate DynSyn's efficiency across various tasks involving different musculoskeletal models, achieving state-of-the-art sample efficiency and robustness compared to baseline algorithms. DynSyn generates interpretable synergistic representations that capture the essential features of dynamical structures and demonstrates generalizability across diverse motor tasks.

Yunyue Wei, Chenhui Zuo, Shanning Zhuang et al.

The embodied learning of human motor control requires whole-body neuro-actuated musculoskeletal dynamics, while the internal muscle-driven processes underlying movement remain inaccessible to direct measurement. Computational modeling offers an alternative, but inverse dynamics methods struggled to resolve redundant control from observed kinematics in the high-dimensional, over-actuated system. Forward imitation approaches based on deep reinforcement learning exhibited inadequate tracking performance due to the curse of dimensionality in both control and reward design. Here we introduce a large-scale parallel musculoskeletal computation framework for biomechanically grounded whole-body motion reproduction. By integrating large-scale parallel GPU simulation with adversarial reward aggregation and value-guided flow exploration, the MS-Emulator framework overcomes key optimization bottlenecks in high-dimensional reinforcement learning for musculoskeletal control, which accurately reproduces a broad repertoire of motions in a whole-body human musculoskeletal system actuated by approximately 700 muscles. It achieved high joint angle accuracy and body position alignment for highly dynamic tasks such as dance, cartwheel, and backflip. The framework was also used to explore the musculoskeletal control solution space, identifying distinct musculoskeletal control policies that converge to nearly identical external kinematic and mechanical measurements. This work establishes a tractable computational route to analyzing the specificity and diversity underlying human embodied control of movement. Project page: https://lnsgroup.cc/research/MS-Emulator.

Yunyue Wei, Chenhui Zuo, Yanan Sui

Controlling high-dimensional systems in biological and robotic applications is challenging due to expansive state-action spaces, where effective exploration is critical. Commonly used exploration strategies in reinforcement learning are largely undirected with sharp degradation as action dimensionality grows. Many existing methods resort to dimensionality reduction, which constrains policy expressiveness and forfeits system flexibility. We introduce Q-guided Flow Exploration (Qflex), a scalable reinforcement learning method that conducts exploration directly in the native high-dimensional action space. During training, Qflex traverses actions from a learnable source distribution along a probability flow induced by the learned value function, aligning exploration with task-relevant gradients rather than isotropic noise. Our proposed method substantially outperforms representative online reinforcement learning baselines across diverse high-dimensional continuous-control benchmarks. Qflex also successfully controls a full-body human musculoskeletal model to perform agile, complex movements, demonstrating superior scalability and sample efficiency in very high-dimensional settings. Our results indicate that value-guided flows offer a principled and practical route to exploration at scale.

Chenhui Zuo, Jinhao Xu, Michael Qian Vergnolle et al.

Physical interactive robotics, ranging from wearable devices to collaborative humanoid robots, require close coordination between mechanical design and control. However, evaluating interactive dynamics is challenging due to complex human biomechanics and motor responses. Traditional experiments rely on indirect metrics without measuring human internal states, such as muscle forces or joint loads. To address this issue, we develop a scalable simulation-based framework for the quantitative analysis of physical human-robot interaction. At its core is a full-body musculoskeletal model serving as a predictive surrogate for the human dynamical system. Driven by a reinforcement learning controller, it generates adaptive, physiologically grounded motor behaviors. We employ a sequential training pipeline where the pre-trained human motion control policy acts as a consistent evaluator, making large-scale design space exploration computationally tractable. By simulating the coupled human-robot system, the framework provides access to internal biomechanical metrics, offering a systematic way to concurrently co-optimize a robot's structural parameters and control policy. We demonstrate its capability in optimizing human-exoskeleton interactions, showing improved joint alignment and reduced contact forces. This work establishes embodied human simulation as a scalable paradigm for interactive robotics design.

Bingquan Zhu, Hao Fang, Yanan Sui et al.

Data sharing for medical research has been difficult as open-sourcing clinical data may violate patient privacy. Traditional methods for face de-identification wipe out facial information entirely, making it impossible to analyze facial behavior. Recent advancements on whole-body keypoints detection also rely on facial input to estimate body keypoints. Both facial and body keypoints are critical in some medical diagnoses, and keypoints invariability after de-identification is of great importance. Here, we propose a solution using deepfake technology, the face swapping technique. While this swapping method has been criticized for invading privacy and portraiture right, it could conversely protect privacy in medical video: patients' faces could be swapped to a proper target face and become unrecognizable. However, it remained an open question that to what extent the swapping de-identification method could affect the automatic detection of body keypoints. In this study, we apply deepfake technology to Parkinson's disease examination videos to de-identify subjects, and quantitatively show that: face-swapping as a de-identification approach is reliable, and it keeps the keypoints almost invariant, significantly better than traditional methods. This study proposes a pipeline for video de-identification and keypoint preservation, clearing up some ethical restrictions for medical data sharing. This work could make open-source high quality medical video datasets more feasible and promote future medical research that benefits our society.

Akifumi Wachi, Xun Shen, Yanan Sui

Safety is critical when applying reinforcement learning (RL) to real-world problems. As a result, safe RL has emerged as a fundamental and powerful paradigm for optimizing an agent's policy while incorporating notions of safety. A prevalent safe RL approach is based on a constrained criterion, which seeks to maximize the expected cumulative reward subject to specific safety constraints. Despite recent effort to enhance safety in RL, a systematic understanding of the field remains difficult. This challenge stems from the diversity of constraint representations and little exploration of their interrelations. To bridge this knowledge gap, we present a comprehensive review of representative constraint formulations, along with a curated selection of algorithms designed specifically for each formulation. In addition, we elucidate the theoretical underpinnings that reveal the mathematical mutual relations among common problem formulations. We conclude with a discussion of the current state and future directions of safe reinforcement learning research.

Chenhui Zuo, Kaibo He, Jing Shao et al.

Modeling and control of the human musculoskeletal system is important for understanding human motor functions, developing embodied intelligence, and optimizing human-robot interaction systems. However, current human musculoskeletal models are restricted to a limited range of body parts and often with a reduced number of muscles. There is also a lack of algorithms capable of controlling over 600 muscles to generate reasonable human movements. To fill this gap, we build a musculoskeletal model (MS-Human-700) with 90 body segments, 206 joints, and 700 muscle-tendon units, allowing simulation of full-body dynamics and interaction with various devices. We develop a new algorithm using low-dimensional representation and hierarchical deep reinforcement learning to achieve state-of-the-art full-body control. We validate the effectiveness of our model and algorithm in simulations with real human locomotion data. The musculoskeletal model, along with its control algorithm, will be made available to the research community to promote a deeper understanding of human motion control and better design of interactive robots. Project page: https://lnsgroup.cc/research/MS-Human-700

Zeji Yi, Yunyue Wei, Chu Xin Cheng et al.

Sequential optimization methods are often confronted with the curse of dimensionality in high-dimensional spaces. Current approaches under the Gaussian process framework are still burdened by the computational complexity of tracking Gaussian process posteriors and need to partition the optimization problem into small regions to ensure exploration or assume an underlying low-dimensional structure. With the idea of transiting the candidate points towards more promising positions, we propose a new method based on Markov Chain Monte Carlo to efficiently sample from an approximated posterior. We provide theoretical guarantees of its convergence in the Gaussian process Thompson sampling setting. We also show experimentally that both the Metropolis-Hastings and the Langevin Dynamics version of our algorithm outperform state-of-the-art methods in high-dimensional sequential optimization and reinforcement learning benchmarks.

Yunyue Wei, Vincent Zhuang, Saraswati Soedarmadji et al.

Bayesian optimization is an effective technique for black-box optimization, but its applicability is typically limited to low-dimensional and small-budget problems due to the cubic complexity of computing the Gaussian process (GP) surrogate. While various approximate GP models have been employed to scale Bayesian optimization to larger sample sizes, most suffer from overly-smooth estimation and focus primarily on problems that allow for large online samples. In this work, we argue that Bayesian optimization algorithms with sparse GPs can more efficiently allocate their representational power to relevant regions of the search space. To achieve this, we propose focalized GP, which leverages a novel variational loss function to achieve stronger local prediction, as well as FocalBO, which hierarchically optimizes the focalized GP acquisition function over progressively smaller search spaces. Experimental results demonstrate that FocalBO can efficiently leverage large amounts of offline and online data to achieve state-of-the-art performance on robot morphology design and to control a 585-dimensional musculoskeletal system.

Yunyue Wei, Zeji Yi, Hongda Li et al.

Learning to move is a primary goal for animals and robots, where ensuring safety is often important when optimizing control policies on the embodied systems. For complex tasks such as the control of human or humanoid control, the high-dimensional parameter space adds complexity to the safe optimization effort. Current safe exploration algorithms exhibit inefficiency and may even become infeasible with large high-dimensional input spaces. Furthermore, existing high-dimensional constrained optimization methods neglect safety in the search process. In this paper, we propose High-dimensional Safe Bayesian Optimization with local optimistic exploration (HdSafeBO), a novel approach designed to handle high-dimensional sampling problems under probabilistic safety constraints. We introduce a local optimistic strategy to efficiently and safely optimize the objective function, providing a probabilistic safety guarantee and a cumulative safety violation bound. Through the use of isometric embedding, HdSafeBO addresses problems ranging from a few hundred to several thousand dimensions while maintaining safety guarantees. To our knowledge, HdSafeBO is the first algorithm capable of optimizing the control of high-dimensional musculoskeletal systems with high safety probability. We also demonstrate the real-world applicability of HdSafeBO through its use in the safe online optimization of neural stimulation induced human motion control.

Chengtian Ma, Yunyue Wei, Chenhui Zuo et al.

Balance control is important for human and bipedal robotic systems. While dynamic balance during locomotion has received considerable attention, quantitative understanding of static balance and falling remains limited. This work presents a hierarchical control pipeline for simulating human balance via a comprehensive whole-body musculoskeletal system. We identified spatiotemporal dynamics of balancing during stable standing, revealed the impact of muscle injury on balancing behavior, and generated fall contact patterns that aligned with clinical data. Furthermore, our simulated hip exoskeleton assistance demonstrated improvement in balance maintenance and reduced muscle effort under perturbation. This work offers unique muscle-level insights into human balance dynamics that are challenging to capture experimentally. It could provide a foundation for developing targeted interventions for individuals with balance impairments and support the advancement of humanoid robotic systems.

Zhengfei Zhang, Yunyue Wei, Yanan Sui

Sample efficiency is crucial in optimization, particularly in black-box scenarios characterized by expensive evaluations and zeroth-order feedback. When computing resources are plentiful, Bayesian optimization is often favored over evolution strategies. In this paper, we introduce a full invariance oriented evolution strategies algorithm, derived from its corresponding framework, that effectively rivals the leading Bayesian optimization method in tasks with dimensions at the upper limit of Bayesian capability. Specifically, we first build the framework InvIGO that fully incorporates historical information while retaining the full invariant and computational complexity. We then exemplify InvIGO on multi-dimensional Gaussian, which gives an invariant and scalable optimizer SynCMA . The theoretical behavior and advantages of our algorithm over other Gaussian-based evolution strategies are further analyzed. Finally, We benchmark SynCMA against leading algorithms in Bayesian optimization and evolution strategies on various high dimension tasks, in cluding Mujoco locomotion tasks, rover planning task and synthetic functions. In all scenarios, SynCMA demonstrates great competence, if not dominance, over other algorithms in sample efficiency, showing the underdeveloped potential of property oriented evolution strategies.

Zehao Jin, Yanan Sui

The whole-brain connectome of a fruit fly comprises over 130K neurons connected with a probability of merely 0.02%, yet achieves an average shortest path of only 4.4 hops. Despite being highly structured at the circuit level, the network's long-range connections are broadly distributed across brain regions, functioning as stochastic shortcuts that enable efficient global communication. Inspired by this observation, we propose Stochastic Attention (SA), a drop-in enhancement for sliding-window attention (SWA) that applies a random permutation to the token sequence before windowed attention and restores the original order afterward. This transforms the fixed local window into a stochastic global one within the same $O(nw)$ per-layer budget. Through depth, independently sampled permutations yield exponentially growing receptive fields, achieving full sequence coverage in $O(\log_w n)$ layers versus $O(n/w)$ for SWA. We validate SA in two settings: pre-training language models from scratch, where a gated SA + SWA combination achieves the best average zero-shot accuracy, and training-free inference on Qwen3-8B and Qwen3-30B-A3B, where SA consistently outperforms SWA and matches or exceeds Mixture of Block Attention at comparable compute budgets. These results suggest that connectome-inspired stochastic routing is a practical primitive for improving the expressivity of efficient attention, complementary to existing linear and sparse approaches.

Zehao Jin, Yaoye Zhu, Chen Zhang et al.

Whole-brain biological neural networks naturally support the learning and control of whole-body movements. However, the use of brain connectomes as neural network controllers in embodied reinforcement learning remains unexplored. We investigate using the exact neural architecture of an adult fruit fly's brain for the control of its body movement. We develop Fly-connectomic Graph Model (FlyGM), whose static structure is identical to the complete connectome of an adult Drosophila for whole-body locomotion control. To perform dynamical control, FlyGM represents the static connectome as a directed message-passing graph to impose a biologically grounded information flow from sensory inputs to motor outputs. Integrated with a biomechanical fruit fly model, our method achieves stable control across diverse locomotion tasks without task-specific architectural tuning. To verify the structural advantages of the connectome-based model, we compare it against a degree-preserving rewired graph, a random graph, and multilayer perceptrons, showing that FlyGM yields higher sample efficiency and superior performance. This work demonstrates that static brain connectomes can be transformed to instantiate effective neural policy for embodied learning of movement control.

Chenhui Zuo, Guohao Lin, Chen Zhang et al.

Coordinated human movement depends on the integration of multisensory inputs, sensorimotor transformation, and motor execution, as well as sensory feedback resulting from body-environment interaction. Building dynamic models of the sensory-musculoskeletal system is essential for understanding movement control and investigating human behaviours. Here, we report a human sensory-musculoskeletal model, termed SMS-Human, that integrates precise anatomical representations of bones, joints, and muscle-tendon units with multimodal sensory inputs involving visual, vestibular, proprioceptive, and tactile components. A stage-wise hierarchical deep reinforcement learning framework was developed to address the inherent challenges of high-dimensional control in musculoskeletal systems with integrated multisensory information. Using this framework, we demonstrated the simulation of three representative movement tasks, including bipedal locomotion, vision-guided object manipulation, and human-machine interaction during bicycling. Our results showed a close resemblance between natural and simulated human motor behaviours. The simulation also revealed musculoskeletal dynamics that could not be directly measured. This work sheds deeper insights into the sensorimotor dynamics of human movements, facilitates quantitative understanding of human behaviours in interactive contexts, and informs the design of systems with embodied intelligence.

Zhengfei Zhang, Kishan Panaganti, Laixi Shi et al.

We study the problem of Distributionally Robust Constrained RL (DRC-RL), where the goal is to maximize the expected reward subject to environmental distribution shifts and constraints. This setting captures situations where training and testing environments differ, and policies must satisfy constraints motivated by safety or limited budgets. Despite significant progress toward algorithm design for the separate problems of distributionally robust RL and constrained RL, there do not yet exist algorithms with end-to-end convergence guarantees for DRC-RL. We develop an algorithmic framework based on strong duality that enables the first efficient and provable solution in a class of environmental uncertainties. Further, our framework exposes an inherent structure of DRC-RL that arises from the combination of distributional robustness and constraints, which prevents a popular class of iterative methods from tractably solving DRC-RL, despite such frameworks being applicable for each of distributionally robust RL and constrained RL individually. Finally, we conduct experiments on a car racing benchmark to evaluate the effectiveness of the proposed algorithm.

Akifumi Wachi, Yunyue Wei, Yanan Sui

Safe exploration is a key to applying reinforcement learning (RL) in safety-critical systems. Existing safe exploration methods guaranteed safety under the assumption of regularity, and it has been difficult to apply them to large-scale real problems. We propose a novel algorithm, SPO-LF, that optimizes an agent's policy while learning the relation between a locally available feature obtained by sensors and environmental reward/safety using generalized linear function approximations. We provide theoretical guarantees on its safety and optimality. We experimentally show that our algorithm is 1) more efficient in terms of sample complexity and computational cost and 2) more applicable to large-scale problems than previous safe RL methods with theoretical guarantees, and 3) comparably sample-efficient and safer compared with existing advanced deep RL methods with safety constraints.

Songyuan Zhang, Zhangjie Cao, Dorsa Sadigh et al.

Most existing imitation learning approaches assume the demonstrations are drawn from experts who are optimal, but relaxing this assumption enables us to use a wider range of data. Standard imitation learning may learn a suboptimal policy from demonstrations with varying optimality. Prior works use confidence scores or rankings to capture beneficial information from demonstrations with varying optimality, but they suffer from many limitations, e.g., manually annotated confidence scores or high average optimality of demonstrations. In this paper, we propose a general framework to learn from demonstrations with varying optimality that jointly learns the confidence score and a well-performing policy. Our approach, Confidence-Aware Imitation Learning (CAIL) learns a well-performing policy from confidence-reweighted demonstrations, while using an outer loss to track the performance of our model and to learn the confidence. We provide theoretical guarantees on the convergence of CAIL and evaluate its performance in both simulated and real robot experiments. Our results show that CAIL significantly outperforms other imitation learning methods from demonstrations with varying optimality. We further show that even without access to any optimal demonstrations, CAIL can still learn a successful policy, and outperforms prior work.

Hao Fang, Chen Gong, Chen Zhang et al.

Speech disorders often occur at the early stage of Parkinson's disease (PD). The speech impairments could be indicators of the disorder for early diagnosis, while motor symptoms are not obvious. In this study, we constructed a new speech corpus of Mandarin Chinese and addressed classification of patients with PD. We implemented classical machine learning methods with ranking algorithms for feature selection, convolutional and recurrent deep networks, and an end to end system. Our classification accuracy significantly surpassed state-of-the-art studies. The result suggests that free talk has stronger classification power than standard speech tasks, which could help the design of future speech tasks for efficient early diagnosis of the disease. Based on existing classification methods and our natural speech study, the automatic detection of PD from daily conversation could be accessible to the majority of the clinical population.

Vincent Zhuang, Yanan Sui

Reinforcement learning algorithms typically assume rewards to be sampled from light-tailed distributions, such as Gaussian or bounded. However, a wide variety of real-world systems generate rewards that follow heavy-tailed distributions. We consider such scenarios in the setting of undiscounted reinforcement learning. By constructing a lower bound, we show that the difficulty of learning heavy-tailed rewards asymptotically dominates the difficulty of learning transition probabilities. Leveraging techniques from robust mean estimation, we propose Heavy-UCRL2 and Heavy-Q-Learning, and show that they achieve near-optimal regret bounds in this setting. Our algorithms also naturally generalize to deep reinforcement learning applications; we instantiate Heavy-DQN as an example of this. We demonstrate that all of our algorithms outperform baselines on both synthetic MDPs and standard RL benchmarks.

Kejun Li, Maegan Tucker, Erdem Bıyık et al.

Characterizing what types of exoskeleton gaits are comfortable for users, and understanding the science of walking more generally, require recovering a user's utility landscape. Learning these landscapes is challenging, as walking trajectories are defined by numerous gait parameters, data collection from human trials is expensive, and user safety and comfort must be ensured. This work proposes the Region of Interest Active Learning (ROIAL) framework, which actively learns each user's underlying utility function over a region of interest that ensures safety and comfort. ROIAL learns from ordinal and preference feedback, which are more reliable feedback mechanisms than absolute numerical scores. The algorithm's performance is evaluated both in simulation and experimentally for three non-disabled subjects walking inside of a lower-body exoskeleton. ROIAL learns Bayesian posteriors that predict each exoskeleton user's utility landscape across four exoskeleton gait parameters. The algorithm discovers both commonalities and discrepancies across users' gait preferences and identifies the gait parameters that most influenced user feedback. These results demonstrate the feasibility of recovering gait utility landscapes from limited human trials.

Kuno Kim, Akshat Jindal, Yang Song et al.

We propose a new framework for Imitation Learning (IL) via density estimation of the expert's occupancy measure followed by Maximum Occupancy Entropy Reinforcement Learning (RL) using the density as a reward. Our approach maximizes a non-adversarial model-free RL objective that provably lower bounds reverse Kullback-Leibler divergence between occupancy measures of the expert and imitator. We present a practical IL algorithm, Neural Density Imitation (NDI), which obtains state-of-the-art demonstration efficiency on benchmark control tasks.

Akifumi Wachi, Yanan Sui

Safe reinforcement learning has been a promising approach for optimizing the policy of an agent that operates in safety-critical applications. In this paper, we propose an algorithm, SNO-MDP, that explores and optimizes Markov decision processes under unknown safety constraints. Specifically, we take a stepwise approach for optimizing safety and cumulative reward. In our method, the agent first learns safety constraints by expanding the safe region, and then optimizes the cumulative reward in the certified safe region. We provide theoretical guarantees on both the satisfaction of the safety constraint and the near-optimality of the cumulative reward under proper regularity assumptions. In our experiments, we demonstrate the effectiveness of SNO-MDP through two experiments: one uses a synthetic data in a new, openly-available environment named GP-SAFETY-GYM, and the other simulates Mars surface exploration by using real observation data.

Maegan Tucker, Ellen Novoseller, Claudia Kann et al.

This paper presents a personalized gait optimization framework for lower-body exoskeletons. Rather than optimizing numerical objectives such as the mechanical cost of transport, our approach directly learns from user preferences, e.g., for comfort. Building upon work in preference-based interactive learning, we present the CoSpar algorithm. CoSpar prompts the user to give pairwise preferences between trials and suggest improvements; as exoskeleton walking is a non-intuitive behavior, users can provide preferences more easily and reliably than numerical feedback. We show that CoSpar performs competitively in simulation and demonstrate a prototype implementation of CoSpar on a lower-body exoskeleton to optimize human walking trajectory features. In the experiments, CoSpar consistently found user-preferred parameters of the exoskeleton's walking gait, which suggests that it is a promising starting point for adapting and personalizing exoskeletons (or other assistive devices) to individual users.

Ellen R. Novoseller, Yibing Wei, Yanan Sui et al.

In preference-based reinforcement learning (RL), an agent interacts with the environment while receiving preferences instead of absolute feedback. While there is increasing research activity in preference-based RL, the design of formal frameworks that admit tractable theoretical analysis remains an open challenge. Building upon ideas from preference-based bandit learning and posterior sampling in RL, we present DUELING POSTERIOR SAMPLING (DPS), which employs preference-based posterior sampling to learn both the system dynamics and the underlying utility function that governs the preference feedback. As preference feedback is provided on trajectories rather than individual state-action pairs, we develop a Bayesian approach for the credit assignment problem, translating preferences to a posterior distribution over state-action reward models. We prove an asymptotic Bayesian no-regret rate for DPS with a Bayesian linear regression credit assignment model. This is the first regret guarantee for preference-based RL to our knowledge. We also discuss possible avenues for extending the proof methodology to other credit assignment models. Finally, we evaluate the approach empirically, showing competitive performance against existing baselines.

Chien-Yi Chang, De-An Huang, Yanan Sui et al.

We address weakly supervised action alignment and segmentation in videos, where only the order of occurring actions is available during training. We propose Discriminative Differentiable Dynamic Time Warping (D3TW), the first discriminative model using weak ordering supervision. The key technical challenge for discriminative modeling with weak supervision is that the loss function of the ordering supervision is usually formulated using dynamic programming and is thus not differentiable. We address this challenge with a continuous relaxation of the min-operator in dynamic programming and extend the alignment loss to be differentiable. The proposed D3TW innovatively solves sequence alignment with discriminative modeling and end-to-end training, which substantially improves the performance in weakly supervised action alignment and segmentation tasks. We show that our model is able to bypass the degenerated sequence problem usually encountered in previous work and outperform the current state-of-the-art across three evaluation metrics in two challenging datasets.

Yanan Sui, Vincent Zhuang, Joel W. Burdick et al.

Enforcing safety is a key aspect of many problems pertaining to sequential decision making under uncertainty, which require the decisions made at every step to be both informative of the optimal decision and also safe. For example, we value both efficacy and comfort in medical therapy, and efficiency and safety in robotic control. We consider this problem of optimizing an unknown utility function with absolute feedback or preference feedback subject to unknown safety constraints. We develop an efficient safe Bayesian optimization algorithm, StageOpt, that separates safe region expansion and utility function maximization into two distinct stages. Compared to existing approaches which interleave between expansion and optimization, we show that StageOpt is more efficient and naturally applicable to a broader class of problems. We provide theoretical guarantees for both the satisfaction of safety constraints as well as convergence to the optimal utility value. We evaluate StageOpt on both a variety of synthetic experiments, as well as in clinical practice. We demonstrate that StageOpt is more effective than existing safe optimization approaches, and is able to safely and effectively optimize spinal cord stimulation therapy in our clinical experiments.

Yanan Sui, Kun ho Kim, Joel W. Burdick

Spinal cord stimulation has enabled humans with motor complete spinal cord injury (SCI) to independently stand and recover some lost autonomic function. Quantifying the quality of bipedal standing under spinal stimulation is important for spinal rehabilitation therapies and for new strategies that seek to combine spinal stimulation and rehabilitative robots (such as exoskeletons) in real time feedback. To study the potential for automated electromyography (EMG) analysis in SCI, we evaluated the standing quality of paralyzed patients undergoing electrical spinal cord stimulation using both video and multi-channel surface EMG recordings during spinal stimulation therapy sessions. The quality of standing under different stimulation settings was quantified manually by experienced clinicians. By correlating features of the recorded EMG activity with the expert evaluations, we show that multi-channel EMG recording can provide accurate, fast, and robust estimation for the quality of bipedal standing in spinally stimulated SCI patients. Moreover, our analysis shows that the total number of EMG channels needed to effectively predict standing quality can be reduced while maintaining high estimation accuracy, which provides more flexibility for rehabilitation robotic systems to incorporate EMG recordings.

Kun Li, Yanan Sui, Joel W. Burdick

This paper develops an inverse reinforcement learning algorithm aimed at recovering a reward function from the observed actions of an agent. We introduce a strategy to flexibly handle different types of actions with two approximations of the Bellman Optimality Equation, and a Bellman Gradient Iteration method to compute the gradient of the Q-value with respect to the reward function. These methods allow us to build a differentiable relation between the Q-value and the reward function and learn an approximately optimal reward function with gradient methods. We test the proposed method in two simulated environments by evaluating the accuracy of different approximations and comparing the proposed method with existing solutions. The results show that even with a linear reward function, the proposed method has a comparable accuracy with the state-of-the-art method adopting a non-linear reward function, and the proposed method is more flexible because it is defined on observed actions instead of trajectories.

Yanan Sui, Yisong Yue, Joel W. Burdick

We consider sequential decision making under uncertainty, where the goal is to optimize over a large decision space using noisy comparative feedback. This problem can be formulated as a $K$-armed Dueling Bandits problem where $K$ is the total number of decisions. When $K$ is very large, existing dueling bandits algorithms suffer huge cumulative regret before converging on the optimal arm. This paper studies the dueling bandits problem with a large number of arms that exhibit a low-dimensional correlation structure. Our problem is motivated by a clinical decision making process in large decision space. We propose an efficient algorithm CorrDuel which optimizes the exploration/exploitation tradeoff in this large decision space of clinical treatments. More broadly, our approach can be applied to other sequential decision problems with large and structured decision spaces. We derive regret bounds, and evaluate performance in simulation experiments as well as on a live clinical trial of therapeutic spinal cord stimulation. To our knowledge, this marks the first time an online learning algorithm was applied towards spinal cord injury treatments. Our experimental results show the effectiveness and efficiency of our approach.

Yanan Sui, Vincent Zhuang, Joel W. Burdick et al.

The dueling bandits problem is an online learning framework for learning from pairwise preference feedback, and is particularly well-suited for modeling settings that elicit subjective or implicit human feedback. In this paper, we study the problem of multi-dueling bandits with dependent arms, which extends the original dueling bandits setting by simultaneously dueling multiple arms as well as modeling dependencies between arms. These extensions capture key characteristics found in many real-world applications, and allow for the opportunity to develop significantly more efficient algorithms than were possible in the original setting. We propose the \selfsparring algorithm, which reduces the multi-dueling bandits problem to a conventional bandit setting that can be solved using a stochastic bandit algorithm such as Thompson Sampling, and can naturally model dependencies using a Gaussian process prior. We present a no-regret analysis for multi-dueling setting, and demonstrate the effectiveness of our algorithm empirically on a wide range of simulation settings.