Search Results for author:
Found 26 papers, 11 papers with code
Beyond Worst-case Attacks: Robust RL with Adaptive Defense via Non-dominated Policies
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 to adversarial attacks during test time.
Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models
We show that Shadowcast are highly effective in achieving attacker's intentions using as few as 50 poison samples.
O3D: Offline Data-driven Discovery and Distillation for Sequential Decision-Making with Large Language Models
Recent advancements in large language models (LLMs) have exhibited promising performance in solving sequential decision-making problems.
Robustness to Multi-Modal Environment Uncertainty in MARL using Curriculum Learning
This work is the first to formulate the generalised problem of robustness to multi-modal environment uncertainty in MARL.
COPlanner: Plan to Roll Out Conservatively but to Explore Optimistically for Model-Based RL
In this paper, we propose $\texttt{COPlanner}$, a planning-driven framework for model-based methods to address the inaccurately learned dynamics model problem with conservative model rollouts and optimistic environment exploration.
Learning Generalizable Agents via Saliency-Guided Features Decorrelation
Our experimental results demonstrate that SGFD can generalize well on a wide range of test environments and significantly outperforms state-of-the-art methods in handling both task-irrelevant variations and task-relevant variations.
Equal Long-term Benefit Rate: Adapting Static Fairness Notions to Sequential Decision Making
Moreover, we show that the policy gradient of Long-term Benefit Rate can be analytically reduced to standard policy gradient.
Game-Theoretic Robust Reinforcement Learning Handles Temporally-Coupled Perturbations
To tackle this challenge, we propose GRAD, a novel game-theoretic approach that treats the temporally-coupled robust RL problem as a partially observable two-player zero-sum game.
Is Imitation All You Need? Generalized Decision-Making with Dual-Phase Training
We introduce DualMind, a generalist agent designed to tackle various decision-making tasks that addresses challenges posed by current methods, such as overfitting behaviors and dependence on task-specific fine-tuning.
TACO: Temporal Latent Action-Driven Contrastive Loss for Visual Reinforcement Learning
Despite recent progress in reinforcement learning (RL) from raw pixel data, sample inefficiency continues to present a substantial obstacle.
A Simple Unified Uncertainty-Guided Framework for Offline-to-Online Reinforcement Learning
However, constrained by the limited quality of the offline dataset, its performance is often sub-optimal.
Instructed Diffuser with Temporal Condition Guidance for Offline Reinforcement Learning
Recent works have shown the potential of diffusion models in computer vision and natural language processing.
Rethinking Adversarial Policies: A Generalized Attack Formulation and Provable Defense in RL
To address these limitations, we introduce a generalized attack framework that has the flexibility to model to what extent the adversary is able to control the agent, and allows the attacker to regulate the state distribution shift and produce stealthier adversarial policies.
Exploring and Exploiting Decision Boundary Dynamics for Adversarial Robustness
However, it is unclear whether existing robust training methods effectively increase the margin for each vulnerable point during training.
SMART: Self-supervised Multi-task pretrAining with contRol Transformers
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 representations without explicit labels.
Provable Unrestricted Adversarial Training without Compromise with Generalizability
Second, the existing AT methods often achieve adversarial robustness at the expense of standard generalizability (i. e., the accuracy on natural examples) because they make a tradeoff between them.
Adversarial Auto-Augment with Label Preservation: A Representation Learning Principle Guided Approach
In experiments, we show that our method consistently brings non-trivial improvements to the three aforementioned learning tasks from both efficiency and final performance, either or not combined with strong pre-defined augmentations, e. g., on medical images when domain knowledge is unavailable and the existing augmentation techniques perform poorly.
Distributional Reward Estimation for Effective Multi-Agent Deep Reinforcement Learning
Our main idea is to design the multi-action-branch reward estimation and policy-weighted reward aggregation for stabilized training.
Multi-agent Reinforcement Learning
reinforcement-learning
+1
Efficient Adversarial Training without Attacking: Worst-Case-Aware Robust Reinforcement Learning
Recent studies reveal that a well-trained deep reinforcement learning (RL) policy can be particularly vulnerable to adversarial perturbations on input observations.
Certifiably Robust Policy Learning against Adversarial Communication in Multi-agent Systems
Communication is important in many multi-agent reinforcement learning (MARL) problems for agents to share information and make good decisions.
Transfer RL across Observation Feature Spaces via Model-Based Regularization
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 dramatic changes over time (e. g. increased number of observable features).
Who Is the Strongest Enemy? Towards Optimal and Efficient Evasion Attacks in Deep RL
Existing works on adversarial RL either use heuristics-based methods that may not find the strongest adversary, or directly train an RL-based adversary by treating the agent as a part of the environment, which can find the optimal adversary but may become intractable in a large state space.
Vulnerability-Aware Poisoning Mechanism for Online RL with Unknown Dynamics
Poisoning attacks on Reinforcement Learning (RL) systems could take advantage of RL algorithm's vulnerabilities and cause failure of the learning.
TempLe: Learning Template of Transitions for Sample Efficient Multi-task RL
Transferring knowledge among various environments is important to efficiently learn multiple tasks online.
Understanding Generalization in Deep Learning via Tensor Methods
Recently proposed complexity measures have provided insights to understanding the generalizability in neural networks from perspectives of PAC-Bayes, robustness, overparametrization, compression and so on.
Can Agents Learn by Analogy? An Inferable Model for PAC Reinforcement Learning
We propose a new model-based method called Greedy Inference Model (GIM) that infers the unknown dynamics from known dynamics based on the internal spectral properties of the environment.
Model-based Reinforcement Learning
reinforcement-learning
+1
