15 citations · 105 across the 36 of their papers we have counts for
24 papers · 1 filter
RLAX: Large-Scale, Distributed Reinforcement Learning for Large Language Models on TPUs
Runlong Zhou, Lefan Zhang, Shang-Chen Wu +29
Reinforcement learning (RL) has emerged as the de-facto paradigm for improving the reasoning capabilities of large language models (LLMs). We have developed RLAX, a scalable RL fra…
Statistical Guarantees for Lifelong Reinforcement Learning using PAC-Bayes Theory
Zhi Zhang, Chris Chow, Yasi Zhang +7
Lifelong reinforcement learning (RL) has been developed as a paradigm for extending single-task RL to more realistic, dynamic settings. In lifelong RL, the "life" of an RL agent is…
Beyond Worst-case Attacks: Robust RL with Adaptive Defense via Non-dominated Policies
Xiangyu Liu, Chenghao Deng, Yanchao Sun +2
In light of the burgeoning success of reinforcement learning (RL) in diverse real-world applications, considerable focus has been directed towards ensuring RL policies are robust t…
Robustness to Multi-Modal Environment Uncertainty in MARL using Curriculum Learning
Aakriti Agrawal, Rohith Aralikatti, Yanchao Sun +1
Multi-agent reinforcement learning (MARL) plays a pivotal role in tackling real-world challenges. However, the seamless transition of trained policies from simulations to real-worl…
COPlanner: Plan to Roll Out Conservatively but to Explore Optimistically for Model-Based RL
Xiyao Wang, Ruijie Zheng, Yanchao Sun +4
Dyna-style model-based reinforcement learning contains two phases: model rollouts to generate sample for policy learning and real environment exploration using current policy for d…
Adapting Static Fairness to Sequential Decision-Making: Bias Mitigation Strategies towards Equal Long-term Benefit Rate
Yuancheng Xu, Chenghao Deng, Yanchao Sun +4
Decisions made by machine learning models can have lasting impacts, making long-term fairness a critical consideration. It has been observed that ignoring the long-term effect and…
Game-Theoretic Robust Reinforcement Learning Handles Temporally-Coupled Perturbations
Yongyuan Liang, Yanchao Sun, Ruijie Zheng +5
Deploying reinforcement learning (RL) systems requires robustness to uncertainty and model misspecification, yet prior robust RL methods typically only study noise introduced indep…
Instructed Diffuser with Temporal Condition Guidance for Offline Reinforcement Learning
Jifeng Hu, Yanchao Sun, Sili Huang +6
Recent works have shown the potential of diffusion models in computer vision and natural language processing. Apart from the classical supervised learning fields, diffusion models…
TACO: Temporal Latent Action-Driven Contrastive Loss for Visual Reinforcement Learning
Ruijie Zheng, Xiyao Wang, Yanchao Sun +5
Despite recent progress in reinforcement learning (RL) from raw pixel data, sample inefficiency continues to present a substantial obstacle. Prior works have attempted to address t…
A Simple Unified Uncertainty-Guided Framework for Offline-to-Online Reinforcement Learning
Siyuan Guo, Yanchao Sun, Jifeng Hu +5
Offline reinforcement learning (RL) provides a promising solution to learning an agent fully relying on a data-driven paradigm. However, constrained by the limited quality of the o…
Rethinking Adversarial Policies: A Generalized Attack Formulation and Provable Defense in RL
Xiangyu Liu, Souradip Chakraborty, Yanchao Sun +1
Most existing works focus on direct perturbations to the victim's state/action or the underlying transition dynamics to demonstrate the vulnerability of reinforcement learning agen…
Exploring and Exploiting Decision Boundary Dynamics for Adversarial Robustness
Yuancheng Xu, Yanchao Sun, Micah Goldblum +2
The robustness of a deep classifier can be characterized by its margins: the decision boundary's distances to natural data points. However, it is unclear whether existing robust tr…
SMART: Self-supervised Multi-task pretrAining with contRol Transformers
Yanchao Sun, Shuang Ma, Ratnesh Madaan +3
Self-supervised pretraining has been extensively studied in language and vision domains, where a unified model can be easily adapted to various downstream tasks by pretraining repr…
Provable Unrestricted Adversarial Training without Compromise with Generalizability
Lilin Zhang, Ning Yang, Yanchao Sun +1
Adversarial training (AT) is widely considered as the most promising strategy to defend against adversarial attacks and has drawn increasing interest from researchers. However, the…
Adversarial Auto-Augment with Label Preservation: A Representation Learning Principle Guided Approach
Kaiwen Yang, Yanchao Sun, Jiahao Su +5
Data augmentation is a critical contributing factor to the success of deep learning but heavily relies on prior domain knowledge which is not always available. Recent works on auto…
Distributional Reward Estimation for Effective Multi-Agent Deep Reinforcement Learning
Jifeng Hu, Yanchao Sun, Hechang Chen +4
Multi-agent reinforcement learning has drawn increasing attention in practice, e.g., robotics and automatic driving, as it can explore optimal policies using samples generated by i…
Efficient Adversarial Training without Attacking: Worst-Case-Aware Robust Reinforcement Learning
Yongyuan Liang, Yanchao Sun, Ruijie Zheng +1
Recent studies reveal that a well-trained deep reinforcement learning (RL) policy can be particularly vulnerable to adversarial perturbations on input observations. Therefore, it i…
Certifiably Robust Policy Learning against Adversarial Communication in Multi-agent Systems
Yanchao Sun, Ruijie Zheng, Parisa Hassanzadeh +4
Communication is important in many multi-agent reinforcement learning (MARL) problems for agents to share information and make good decisions. However, when deploying trained commu…
Transfer RL across Observation Feature Spaces via Model-Based Regularization
Yanchao Sun, Ruijie Zheng, Xiyao Wang +2
In many reinforcement learning (RL) applications, the observation space is specified by human developers and restricted by physical realizations, and may thus be subject to dramati…
Who Is the Strongest Enemy? Towards Optimal and Efficient Evasion Attacks in Deep RL
Yanchao Sun, Ruijie Zheng, Yongyuan Liang +1
Evaluating the worst-case performance of a reinforcement learning (RL) agent under the strongest/optimal adversarial perturbations on state observations (within some constraints) i…
Vulnerability-Aware Poisoning Mechanism for Online RL with Unknown Dynamics
Yanchao Sun, Da Huo, Furong Huang
Poisoning attacks on Reinforcement Learning (RL) systems could take advantage of RL algorithm's vulnerabilities and cause failure of the learning. However, prior works on poisoning…
TempLe: Learning Template of Transitions for Sample Efficient Multi-task RL
Yanchao Sun, Xiangyu Yin, Furong Huang
Transferring knowledge among various environments is important to efficiently learn multiple tasks online. Most existing methods directly use the previously learned models or previ…
Understanding Generalization in Deep Learning via Tensor Methods
Jingling Li, Yanchao Sun, Jiahao Su +2
Deep neural networks generalize well on unseen data though the number of parameters often far exceeds the number of training examples. Recently proposed complexity measures have pr…
Can Agents Learn by Analogy? An Inferable Model for PAC Reinforcement Learning
Yanchao Sun, Furong Huang
Model-based reinforcement learning algorithms make decisions by building and utilizing a model of the environment. However, none of the existing algorithms attempts to infer the dy…