Zero-sum Markov games arise in a wide variety of sequential decision-making problems such as adversarial learning and planning against modeled uncertainties. However, prior work on finite-sample guarantees on the learned state-action value function ($Q$-function) for zero-sum Markov games is largely restricted to finit...
Kushagra Gupta, Jing-Qi Li, Caden Armstrong et al.· 0 citations
When interacting with an unfamiliar deformable material, a robot lacks prior knowledge of its physical properties and how it will respond to applied forces and motion. Rapid online identification is therefore essential for reliable manipulation. We present FORM (From Observed Response to Material laws), which identifie...
S. Tretiakov, Rui-Han Zhao, Cheng-Hsi Hsiao et al.· 0 citations
The chance-constrained correlated equilibrium concept provides a robust coordination technique for self-interested agents whose costs are uncertain to a central coordinator, but the number of joint actions considered in its computation grows exponentially with the number of agents. We propose an exact-one resource-assi...
Jaehan Im, U. Topcu, David Fridovich-Keil· 0 citations
Policy gradient methods for on-policy reinforcement learning (RL) can become unstable when expensive, scarce target-domain data yield noisy gradient estimates. We address this challenge by complementing limited high-fidelity (HF) target-domain data with abundant, cheap, but biased low-fidelity (LF) data, e.g., from a s...
Xin-Jie Liu, Rui-Han Zhao, A. Chaudhuri et al.· 0 citations
In this work, we present a simple method to engineer a small neural network to control power converters. Learning-based methods have emerged as a promising approach for power converter control over wide operating point variations. However, many of these approaches do not exploit the analytical structure of converter dy...
Kamakshi Tatkare, U. Topcu, B. Johnson· 0 citations
Vision-language navigation agents are often evaluated on their ability to follow route-like instructions toward a fixed goal. Yet, real navigation instructions often depend on observed states of the environment: if a condition holds, then follow one path, otherwise take another. Such instructions require an agent to ev...
Seoyoung Lee, N. Bhatt, Pranay Samineni et al.· 0 citations
Analyzing LLMs'internal processes can expose systematic vulnerabilities that warrant caution before deploying LLMs in strategic domains without robust guardrails, showing how analyzing LLMs'internal processes can expose systematic vulnerabilities that warrant caution before deploying LLMs in strategic domains without r...
Jan Sobotka, M. Karabag, U. Topcu· arXiv.org· 2 citations
The notion of $\alpha$-robustness, a measure of the guaranteed utility each agent retains while pursuing its optimal single agent policy, is introduced, assuming all agents obey the social law.
Rolando Fernandez, Caleb Probine, Tyler Lee et al.· 0 citations
The Temporal-Logic-based Causal Diagram (TL-CD) in RL is proposed, which captures the temporal causal relationships between different properties of the environment and the benefits of using TL-CDs are demonstrated, particularly the faster convergence of the algorithm to an optimal policy due to reduced exploration of t...
Yashi Paliwal, Rajarshi Roy, Jean-Raphaël Gaglione et al.· International Cross-Domain C...· 5 citations
ViewMind3D is presented, a fully training-free and modular framework for 3D spatial reasoning over multi-view observations of a scene without requiring complete 3D reconstruction, which improves performance on spatially grounded question types, such as ``What''questions in SQA3D, while maintaining strong overall accura...
Ping-Kun Chiang, Kun-Ru Wu, Po-han Li et al.· arXiv.org· 0 citations
A reinforcement learning (RL)-based air traffic management system that integrates both noise and safety considerations within a unified, decentralized framework and demonstrates strong performance across both objectives and reveals tradeoffs among separation, noise exposure, and energy efficiency under high traffic den...
CL4AD is presented, the first integration of curriculum learning into batched autonomous driving simulators by framing scenario selection as an unsupervised environment design problem, and utility functions that shape curricula based on success rates and the realism of the agent's behavior are introduced, in addition t...
Cevahir Koprulu, D. Paz, Feng Tao et al.· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
