Zobrazeno 1 - 10
of 32
pro vyhledávání: '"Jin, Tiancheng"'
Autor:
Jin, Tiancheng, Zhao, Jianjun
Ensuring the correctness of quantum programs is crucial for quantum software quality assurance. Although various effective verification methods exist for classical programs, they cannot be applied to quantum programs due to the fundamental difference
Externí odkaz:
http://arxiv.org/abs/2306.06468
Existing online learning algorithms for adversarial Markov Decision Processes achieve ${O}(\sqrt{T})$ regret after $T$ rounds of interactions even if the loss functions are chosen arbitrarily by an adversary, with the caveat that the transition funct
Externí odkaz:
http://arxiv.org/abs/2305.17380
Code classification is a difficult issue in program understanding and automatic coding. Due to the elusive syntax and complicated semantics in programs, most existing studies use techniques based on abstract syntax tree (AST) and graph neural network
Externí odkaz:
http://arxiv.org/abs/2305.04228
We study the problem of designing adaptive multi-armed bandit algorithms that perform optimally in both the stochastic setting and the adversarial setting simultaneously (often known as a best-of-both-world guarantee). A line of recent works shows th
Externí odkaz:
http://arxiv.org/abs/2302.13534
The standard assumption in reinforcement learning (RL) is that agents observe feedback for their actions immediately. However, in practice feedback is often observed in delay. This paper studies online learning in episodic Markov decision process (MD
Externí odkaz:
http://arxiv.org/abs/2201.13172
We consider the best-of-both-worlds problem for learning an episodic Markov Decision Process through $T$ episodes, with the goal of achieving $\widetilde{\mathcal{O}}(\sqrt{T})$ regret when the losses are adversarial and simultaneously $\mathcal{O}(\
Externí odkaz:
http://arxiv.org/abs/2106.04117
Autor:
Jin, Tiancheng, Luo, Haipeng
This work studies the problem of learning episodic Markov Decision Processes with known transition and bandit feedback. We develop the first algorithm with a ``best-of-both-worlds'' guarantee: it achieves $\mathcal{O}(log T)$ regret when the losses a
Externí odkaz:
http://arxiv.org/abs/2006.05606
We consider the problem of learning in episodic finite-horizon Markov decision processes with an unknown transition function, bandit feedback, and adversarial losses. We propose an efficient algorithm that achieves $\mathcal{\tilde{O}}(L|X|\sqrt{|A|T
Externí odkaz:
http://arxiv.org/abs/1912.01192
Autor:
Holler, John, Vuorio, Risto, Qin, Zhiwei, Tang, Xiaocheng, Jiao, Yan, Jin, Tiancheng, Singh, Satinder, Wang, Chenxi, Ye, Jieping
Order dispatching and driver repositioning (also known as fleet management) in the face of spatially and temporally varying supply and demand are central to a ride-sharing platform marketplace. Hand-crafting heuristic solutions that account for the d
Externí odkaz:
http://arxiv.org/abs/1911.11260
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.