اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدBeating Stochastic and Adversarial Semi-bandits Optimally and Simultaneously
144
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
We develop the first general semi-bandit algorithm that simultaneously achieves $mathcal{O}(log T)$ regret for stochastic environments and $mathcal{O}(sqrt{T})$ regret for adversarial environments without knowledge of the regime or the number of rounds $T$. The leading problem-dependent constants of our bounds are not only optimal in some worst-case sense studied previously, but also optimal for two concrete instances of semi-bandit problems. Our algorithm and analysis extend the recent work of (Zimmert & Seldin, 2019) for the special case of multi-armed bandit, but importantly requires a novel hybrid regularizer designed specifically for semi-bandit. Experimental results on synthetic data show that our algorithm indeed performs well uniformly over different environments. We finally provide a preliminary extension of our results to the full bandit feedback.
قيم البحث
اقرأ أيضاً
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 are
stochastic, and simultaneously enjoys worst-case robustness with $tilde{mathcal{O}}(sqrt{T})$ regret even when the losses are adversarial, where $T$ is the number of episodes. More generally, it achieves $tilde{mathcal{O}}(sqrt{C})$ regret in an intermediate setting where the losses are corrupted by a total amount of $C$. Our algorithm is based on the Follow-the-Regularized-Leader method from Zimin and Neu (2013), with a novel hybrid regularizer inspired by recent works of Zimmert et al. (2019a, 2019b) for the special case of multi-armed bandits. Crucially, our regularizer admits a non-diagonal Hessian with a highly complicated inverse. Analyzing such a regularizer and deriving a particular self-bounding regret guarantee is our key technical contribution and might be of independent interest.
We derive an algorithm that achieves the optimal (within constants) pseudo-regret in both adversarial and stochastic multi-armed bandits without prior knowledge of the regime and time horizon. The algorithm is based on online mirror descent (OMD) wit
h Tsallis entropy regularization with power $alpha=1/2$ and reduced-variance loss estimators. More generally, we define an adversarial regime with a self-bounding constraint, which includes stochastic regime, stochastically constrained adversarial regime (Wei and Luo), and stochastic regime with adversarial corruptions (Lykouris et al.) as special cases, and show that the algorithm achieves logarithmic regret guarantee in this regime and all of its special cases simultaneously with the adversarial regret guarantee.} The algorithm also achieves adversarial and stochastic optimality in the utility-based dueling bandit setting. We provide empirical evaluation of the algorithm demonstrating that it significantly outperforms UCB1 and EXP3 in stochastic environments. We also provide examples of adversarial environments, where UCB1 and Thompson Sampling exhibit almost linear regret, whereas our algorithm suffers only logarithmic regret. To the best of our knowledge, this is the first example demonstrating vulnerability of Thompson Sampling in adversarial environments. Last, but not least, we present a general stochastic analysis and a general adversarial analysis of OMD algorithms with Tsallis entropy regularization for $alphain[0,1]$ and explain the reason why $alpha=1/2$ works best.
We propose an algorithm for stochastic and adversarial multiarmed bandits with switching costs, where the algorithm pays a price $lambda$ every time it switches the arm being played. Our algorithm is based on adaptation of the Tsallis-INF algorithm o
f Zimmert and Seldin (2021) and requires no prior knowledge of the regime or time horizon. In the oblivious adversarial setting it achieves the minimax optimal regret bound of $Obig((lambda K)^{1/3}T^{2/3} + sqrt{KT}big)$, where $T$ is the time horizon and $K$ is the number of arms. In the stochastically constrained adversarial regime, which includes the stochastic regime as a special case, it achieves a regret bound of $Oleft(big((lambda K)^{2/3} T^{1/3} + ln Tbig)sum_{i eq i^*} Delta_i^{-1}right)$, where $Delta_i$ are the suboptimality gaps and $i^*$ is a unique optimal arm. In the special case of $lambda = 0$ (no switching costs), both bounds are minimax optimal within constants. We also explore variants of the problem, where switching cost is allowed to change over time. We provide experimental evaluation showing competitiveness of our algorithm with the relevant baselines in the stochastic, stochastically constrained adversarial, and adversarial regimes with fixed switching cost.
We derive improved regret bounds for the Tsallis-INF algorithm of Zimmert and Seldin (2021). We show that in adversarial regimes with a $(Delta,C,T)$ self-bounding constraint the algorithm achieves $mathcal{O}left(left(sum_{i eq i^*} frac{1}{Delta_i}
right)log_+left(frac{(K-1)T}{left(sum_{i eq i^*} frac{1}{Delta_i}right)^2}right)+sqrt{Cleft(sum_{i eq i^*}frac{1}{Delta_i}right)log_+left(frac{(K-1)T}{Csum_{i eq i^*}frac{1}{Delta_i}}right)}right)$ regret bound, where $T$ is the time horizon, $K$ is the number of arms, $Delta_i$ are the suboptimality gaps, $i^*$ is the best arm, $C$ is the corruption magnitude, and $log_+(x) = maxleft(1,log xright)$. The regime includes stochastic bandits, stochastically constrained adversarial bandits, and stochastic bandits with adversarial corruptions as special cases. Additionally, we provide a general analysis, which allows to achieve the same kind of improvement for generalizations of Tsallis-INF to other settings beyond multiarmed bandits.
This paper investigates the adversarial Bandits with Knapsack (BwK) online learning problem, where a player repeatedly chooses to perform an action, pays the corresponding cost, and receives a reward associated with the action. The player is constrai
ned by the maximum budget $B$ that can be spent to perform actions, and the rewards and the costs of the actions are assigned by an adversary. This problem has only been studied in the restricted setting where the reward of an action is greater than the cost of the action, while we provide a solution in the general setting. Namely, we propose EXP3.BwK, a novel algorithm that achieves order optimal regret. We also propose EXP3++.BwK, which is order optimal in the adversarial BwK setup, and incurs an almost optimal expected regret with an additional factor of $log(B)$ in the stochastic BwK setup. Finally, we investigate the case of having large costs for the actions (i.e., they are comparable to the budget size $B$), and show that for the adversarial setting, achievable regret bounds can be significantly worse, compared to the case of having costs bounded by a constant, which is a common assumption within the BwK literature.
الأسئلة المقترحة
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
