我们考虑在具有非线性函数近似的两名玩家零和马尔可夫游戏中学习NASH平衡,其中动作值函数通过繁殖内核Hilbert Space(RKHS)中的函数近似。关键挑战是如何在高维函数空间中进行探索。我们提出了一种新颖的在线学习算法,以最大程度地减少双重性差距来找到NASH平衡。我们算法的核心是基于不确定性的乐观原理得出的上和下置信度界限。我们证明,在非常温和的假设上,我们的算法能够获得$ O(\ sqrt {t})$遗憾,并在对奖励功能和马尔可夫游戏的基本动态下进行多项式计算复杂性。我们还提出了我们的算法的几个扩展,包括具有伯恩斯坦型奖励的算法,可以实现更严格的遗憾,以及用于模型错误指定的另一种算法,可以应用于神经功能近似。
translated by 谷歌翻译
我们与指定为领导者的球员之一和其他球员读为追随者的球员学习多人一般汇总马尔可夫游戏。特别是,我们专注于追随者是近视的游戏,即,他们的目标是最大限度地提高他们的瞬间奖励。对于这样的游戏,我们的目标是找到一个Stackelberg-Nash均衡(SNE),这是一个策略对$(\ pi ^ *,\ nu ^ *)$,这样(i)$ \ pi ^ * $是追随者始终发挥最佳回应的领导者的最佳政策,(ii)$ \ nu ^ * $是追随者的最佳反应政策,这是由$ \ pi ^ *引起的追随者游戏的纳什均衡$。我们开发了用于在线和离线设置中的SNE解决SNE的采样高效的强化学习(RL)算法。我们的算法是最小二乘值迭代的乐观和悲观的变体,并且它们很容易能够在大状态空间的设置中结合函数近似工具。此外,对于线性函数近似的情况,我们证明我们的算法分别在线和离线设置下实现了Sublinear遗憾和次优。据我们所知,我们建立了第一种可用于解决近代Markov游戏的SNES的第一款可透明的RL算法。
translated by 谷歌翻译
我们研究了具有线性函数近似增强学习中的随机最短路径(SSP)问题,其中过渡内核表示为未知模型的线性混合物。我们将此类别的SSP问题称为线性混合物SSP。我们提出了一种具有Hoeffding-type置信度的新型算法,用于学习线性混合物SSP,可以获得$ \ tilde {\ Mathcal {o}}}}(d B _ {\ star}^{1.5} \ sqrt {k/c_ {k/c_ {k/c_ {k/c_ { \ min}})$遗憾。这里$ k $是情节的数量,$ d $是混合模型中功能映射的维度,$ b _ {\ star} $限制了最佳策略的预期累积成本,$ c _ {\ min}>> 0 $是成本函数的下限。当$ c _ {\ min} = 0 $和$ \ tilde {\ mathcal {o}}}(k^{2/3})$遗憾时,我们的算法也适用于情况。据我们所知,这是第一个具有sublrinear遗憾保证线性混合物SSP的算法。此外,我们设计了精致的伯恩斯坦型信心集并提出了改进的算法,该算法可实现$ \ tilde {\ Mathcal {o}}}(d b _ {\ star} \ sqrt {k/c/c/c {k/c _ {\ min}}) $遗憾。为了补充遗憾的上限,我们还证明了$ \ omega(db _ {\ star} \ sqrt {k})$的下限。因此,我们的改进算法将下限匹配到$ 1/\ sqrt {c _ {\ min}} $ factor和poly-logarithmic因素,从而实现了近乎最佳的遗憾保证。
translated by 谷歌翻译
We study reinforcement learning (RL) with linear function approximation. For episodic time-inhomogeneous linear Markov decision processes (linear MDPs) whose transition dynamic can be parameterized as a linear function of a given feature mapping, we propose the first computationally efficient algorithm that achieves the nearly minimax optimal regret $\tilde O(d\sqrt{H^3K})$, where $d$ is the dimension of the feature mapping, $H$ is the planning horizon, and $K$ is the number of episodes. Our algorithm is based on a weighted linear regression scheme with a carefully designed weight, which depends on a new variance estimator that (1) directly estimates the variance of the \emph{optimal} value function, (2) monotonically decreases with respect to the number of episodes to ensure a better estimation accuracy, and (3) uses a rare-switching policy to update the value function estimator to control the complexity of the estimated value function class. Our work provides a complete answer to optimal RL with linear MDPs, and the developed algorithm and theoretical tools may be of independent interest.
translated by 谷歌翻译
我们研究了基于模型的无奖励加强学习,具有ePiSodic Markov决策过程的线性函数近似(MDP)。在此设置中,代理在两个阶段工作。在勘探阶段,代理商与环境相互作用并在没有奖励的情况下收集样品。在规划阶段,代理商给出了特定的奖励功能,并使用从勘探阶段收集的样品来学习良好的政策。我们提出了一种新的可直接有效的算法,称为UCRL-RFE在线性混合MDP假设,其中MDP的转换概率内核可以通过线性函数参数化,在状态,动作和下一个状态的三联体上定义的某些特征映射上参数化。我们展示了获得$ \ epsilon $-Optimal策略进行任意奖励函数,Ucrl-RFE需要以大多数$ \ tilde {\ mathcal {o}}来进行采样(h ^ 5d ^ 2 \ epsilon ^ { - 2})勘探阶段期间的$派对。在这里,$ H $是集的长度,$ d $是特征映射的尺寸。我们还使用Bernstein型奖金提出了一种UCRL-RFE的变种,并表明它需要在大多数$ \ TINDE {\ MATHCAL {o}}(H ^ 4D(H + D)\ epsilon ^ { - 2})进行样本$达到$ \ epsilon $ -optimal政策。通过构建特殊类的线性混合MDPS,我们还证明了对于任何无奖励算法,它需要至少为$ \ TINDE \ OMEGA(H ^ 2d \ epsilon ^ { - 2})$剧集来获取$ \ epsilon $ -optimal政策。我们的上限与依赖于$ \ epsilon $的依赖性和$ d $ if $ h \ ge d $。
translated by 谷歌翻译
We study time-inhomogeneous episodic reinforcement learning (RL) under general function approximation and sparse rewards. We design a new algorithm, Variance-weighted Optimistic $Q$-Learning (VO$Q$L), based on $Q$-learning and bound its regret assuming completeness and bounded Eluder dimension for the regression function class. As a special case, VO$Q$L achieves $\tilde{O}(d\sqrt{HT}+d^6H^{5})$ regret over $T$ episodes for a horizon $H$ MDP under ($d$-dimensional) linear function approximation, which is asymptotically optimal. Our algorithm incorporates weighted regression-based upper and lower bounds on the optimal value function to obtain this improved regret. The algorithm is computationally efficient given a regression oracle over the function class, making this the first computationally tractable and statistically optimal approach for linear MDPs.
translated by 谷歌翻译
我们认为在情节环境中的强化学习(RL)中的遗憾最小化问题。在许多实际的RL环境中,状态和动作空间是连续的或非常大的。现有方法通过随机过渡模型的低维表示或$ q $ functions的近似值来确定遗憾的保证。但是,对国家价值函数的函数近似方案的理解基本上仍然缺失。在本文中,我们提出了一种基于在线模型的RL算法,即CME-RL,该算法将过渡分布的表示形式学习为嵌入在复制的内核希尔伯特领域中的嵌入,同时仔细平衡了利用探索 - 探索权衡取舍。我们通过证明频繁的(最糟糕的)遗憾结束了$ \ tilde {o} \ big(h \ gamma_n \ sqrt {n} \ big)$ \ footnote {$ footnote {$ tilde {$ o}(\ cdot)$仅隐藏绝对常数和poly-logarithmic因素。},其中$ h $是情节长度,$ n $是时间步长的总数,$ \ gamma_n $是信息理论数量国家行动特征空间的有效维度。我们的方法绕过了估计过渡概率的需求,并适用于可以定义内核的任何域。它还为内核方法的一般理论带来了新的见解,以进行近似推断和RL遗憾的最小化。
translated by 谷歌翻译
尽管基于模型的增强学习(RL)方法被认为是更具样本的高效,但现有算法通常依赖于复杂的规划算法与模型学习过程紧密粘合。因此,学习模型可能缺乏与更专业规划者重新使用的能力。在本文中,我们解决了这个问题,并提供了在没有奖励信号的指导的情况下有效地学习RL模型的方法。特别是,我们采取了一个插件求解器方法,我们专注于在探索阶段学习模型,并要求在学习模型上的\ emph {任何规划算法}可以给出近最佳的政策。具体而言,我们专注于线性混合MDP设置,其中概率转换矩阵是一组现有模型的(未知)凸面组合。我们表明,通过建立新的探索算法,即插即用通过\ tilde {o}来学习模型(d ^ 2h ^ 3 / epsilon ^ 2)$与环境交互,\ emph {任何} $ \ epsilon $ -optimal Planner在模型上给出$ O(\ epsilon)$ - 原始模型上的最佳政策。此示例复杂性与非插入方法的下限与下限匹配,并且是\ EMPH {统计上最佳}。我们通过利用使用伯尔斯坦不等式和指定的线性混合MDP的属性来实现仔细的最大总差异来实现这一结果。
translated by 谷歌翻译
鉴于它在提取功能表示方面的力量,对比性的自我监督学习已成功整合到(深)强化学习(RL)的实践中,从而在各种应用程序中提供了有效的政策学习。尽管取得了巨大的经验成功,但对RL的对比学习的理解仍然难以捉摸。为了缩小这样的差距,我们研究了Markov决策过程(MDP)和Markov Games(MGS)的对比度学习如何赋予RL的能力。对于这两种模型,我们建议通过最大程度地减少对比度损失来提取低级别模型的正确特征表示。此外,在在线环境下,我们提出了新颖的上限置信界(UCB)型算法,该算法将这种对比度损失与MDP或MGS的在线RL算法结合在一起。从理论上讲,我们进一步证明了我们的算法恢复了真实表示形式,并同时在学习MDP和MGS中学习最佳策略和NASH平衡方面同时实现了样本效率。我们还提供实证研究,以证明基于UCB的RL的对比度学习方法的功效。据我们所知,我们提供了第一种可证明有效的在线RL算法,该算法结合了代表学习的对比学习。我们的代码可从https://github.com/baichenjia/contrastive-ucb获得。
translated by 谷歌翻译
We study episodic two-player zero-sum Markov games (MGs) in the offline setting, where the goal is to find an approximate Nash equilibrium (NE) policy pair based on a dataset collected a priori. When the dataset does not have uniform coverage over all policy pairs, finding an approximate NE involves challenges in three aspects: (i) distributional shift between the behavior policy and the optimal policy, (ii) function approximation to handle large state space, and (iii) minimax optimization for equilibrium solving. We propose a pessimism-based algorithm, dubbed as pessimistic minimax value iteration (PMVI), which overcomes the distributional shift by constructing pessimistic estimates of the value functions for both players and outputs a policy pair by solving NEs based on the two value functions. Furthermore, we establish a data-dependent upper bound on the suboptimality which recovers a sublinear rate without the assumption on uniform coverage of the dataset. We also prove an information-theoretical lower bound, which suggests that the data-dependent term in the upper bound is intrinsic. Our theoretical results also highlight a notion of "relative uncertainty", which characterizes the necessary and sufficient condition for achieving sample efficiency in offline MGs. To the best of our knowledge, we provide the first nearly minimax optimal result for offline MGs with function approximation.
translated by 谷歌翻译
我们在适应性约束下研究了强化学习(RL),线性函数近似。我们考虑两个流行的有限适应性模型:批量学习模型和稀有策略交换机模型,并提出了两个有效的在线线性马尔可夫决策过程的在线RL算法,其中转换概率和奖励函数可以表示为一些线性函数已知的特征映射。具体而言,对于批量学习模型,我们提出的LSVI-UCB-批处理算法实现了$ \ tilde o(\ sqrt {d ^ 3h ^ 3t} + dht / b)$后悔,$ d $是尺寸特征映射,$ H $是剧集长度,$ t $是交互数量,$ b $是批次数。我们的结果表明,只使用$ \ sqrt {t / dh} $批量来获得$ \ tilde o(\ sqrt {d ^ 3h ^ 3t})$后悔。对于稀有策略开关模型,我们提出的LSVI-UCB-RARESWICH算法享有$ \ TINDE O(\ SQRT {D ^ 3h ^ 3t [1 + T /(DH)] ^ {dh / b})$遗憾,这意味着$ dh \ log t $策略交换机足以获得$ \ tilde o(\ sqrt {d ^ 3h ^ 3t})$后悔。我们的算法达到与LSVI-UCB算法相同的遗憾(Jin等,2019),但具有大量较小的适应性。我们还为批量学习模式建立了较低的界限,这表明对我们遗憾的依赖于您的遗憾界限是紧张的。
translated by 谷歌翻译
Modern Reinforcement Learning (RL) is commonly applied to practical problems with an enormous number of states, where function approximation must be deployed to approximate either the value function or the policy. The introduction of function approximation raises a fundamental set of challenges involving computational and statistical efficiency, especially given the need to manage the exploration/exploitation tradeoff. As a result, a core RL question remains open: how can we design provably efficient RL algorithms that incorporate function approximation? This question persists even in a basic setting with linear dynamics and linear rewards, for which only linear function approximation is needed.This paper presents the first provable RL algorithm with both polynomial runtime and polynomial sample complexity in this linear setting, without requiring a "simulator" or additional assumptions. Concretely, we prove that an optimistic modification of Least-Squares Value Iteration (LSVI)-a classical algorithm frequently studied in the linear setting-achieves O( √ d 3 H 3 T ) regret, where d is the ambient dimension of feature space, H is the length of each episode, and T is the total number of steps. Importantly, such regret is independent of the number of states and actions.
translated by 谷歌翻译
尽管固定环境中的单一机构政策优化最近在增强学习社区中引起了很多研究的关注,但是当在潜在竞争性的环境中有多个代理商在玩耍时,从理论上讲,少得多。我们通过提出和分析具有结构化但未知过渡的零和Markov游戏的新的虚拟游戏策略优化算法来向前迈进。我们考虑两类的过渡结构:分类的独立过渡和单个控制器过渡。对于这两种情况,我们都证明了紧密的$ \ widetilde {\ Mathcal {o}}(\ sqrt {k})$遗憾的范围在$ k $ eviepodes之后,在两种代理竞争的游戏场景中。每个代理人的遗憾是针对潜在的对抗对手的衡量,他们在观察完整的政策序列后可以在事后选择一个最佳政策。我们的算法在非平稳环境中同时进行政策优化的范围下,具有上置信度结合(UCB)的乐观和虚拟游戏的结合。当两个玩家都采用所提出的算法时,他们的总体最优差距为$ \ widetilde {\ Mathcal {o}}(\ sqrt {k})$。
translated by 谷歌翻译
We consider a multi-agent episodic MDP setup where an agent (leader) takes action at each step of the episode followed by another agent (follower). The state evolution and rewards depend on the joint action pair of the leader and the follower. Such type of interactions can find applications in many domains such as smart grids, mechanism design, security, and policymaking. We are interested in how to learn policies for both the players with provable performance guarantee under a bandit feedback setting. We focus on a setup where both the leader and followers are {\em non-myopic}, i.e., they both seek to maximize their rewards over the entire episode and consider a linear MDP which can model continuous state-space which is very common in many RL applications. We propose a {\em model-free} RL algorithm and show that $\tilde{\mathcal{O}}(\sqrt{d^3H^3T})$ regret bounds can be achieved for both the leader and the follower, where $d$ is the dimension of the feature mapping, $H$ is the length of the episode, and $T$ is the total number of steps under the bandit feedback information setup. Thus, our result holds even when the number of states becomes infinite. The algorithm relies on {\em novel} adaptation of the LSVI-UCB algorithm. Specifically, we replace the standard greedy policy (as the best response) with the soft-max policy for both the leader and the follower. This turns out to be key in establishing uniform concentration bound for the value functions. To the best of our knowledge, this is the first sub-linear regret bound guarantee for the Markov games with non-myopic followers with function approximation.
translated by 谷歌翻译
我们研究了线性函数近似的强化学习(RL)。此问题的现有算法仅具有高概率遗憾和/或可能大致正确(PAC)样本复杂性保证,这不能保证对最佳政策的趋同。在本文中,为了克服现有算法的限制,我们提出了一种新的算法,称为长笛,它享有统一-PAC收敛到具有高概率的最佳政策。统一-PAC保证是文献中强化学习的最强烈保证,它可以直接意味着PAC和高概率遗憾,使我们的算法优于具有线性函数近似的所有现有算法。在我们的算法的核心,是一种新颖的最小值函数估计器和多级别分区方案,以从历史观察中选择训练样本。这两种技术都是新的和独立的兴趣。
translated by 谷歌翻译
We study sample efficient reinforcement learning (RL) under the general framework of interactive decision making, which includes Markov decision process (MDP), partially observable Markov decision process (POMDP), and predictive state representation (PSR) as special cases. Toward finding the minimum assumption that empowers sample efficient learning, we propose a novel complexity measure, generalized eluder coefficient (GEC), which characterizes the fundamental tradeoff between exploration and exploitation in online interactive decision making. In specific, GEC captures the hardness of exploration by comparing the error of predicting the performance of the updated policy with the in-sample training error evaluated on the historical data. We show that RL problems with low GEC form a remarkably rich class, which subsumes low Bellman eluder dimension problems, bilinear class, low witness rank problems, PO-bilinear class, and generalized regular PSR, where generalized regular PSR, a new tractable PSR class identified by us, includes nearly all known tractable POMDPs. Furthermore, in terms of algorithm design, we propose a generic posterior sampling algorithm, which can be implemented in both model-free and model-based fashion, under both fully observable and partially observable settings. The proposed algorithm modifies the standard posterior sampling algorithm in two aspects: (i) we use an optimistic prior distribution that biases towards hypotheses with higher values and (ii) a loglikelihood function is set to be the empirical loss evaluated on the historical data, where the choice of loss function supports both model-free and model-based learning. We prove that the proposed algorithm is sample efficient by establishing a sublinear regret upper bound in terms of GEC. In summary, we provide a new and unified understanding of both fully observable and partially observable RL.
translated by 谷歌翻译
我们提出了一种乐观的基于模型的算法,Dubbed SMRL,用于通过指数族分布指定的转换模型,以D $参数指定,奖励是有界和已知的。SMRL使用得分匹配,一种无通量的密度估计技术,可以通过RIDGE回归有效地估计模型参数。在标准规律性假设下,SMRL实现$ \ tilde o(d \ sqrt {h ^ 3t})$在线遗憾,其中$ h $是每一集的长度,$ t $是互动的总数(忽略多项式依赖结构尺度参数)。
translated by 谷歌翻译
我们研究了马尔可夫潜在游戏(MPG)中多机构增强学习(RL)问题的策略梯度方法的全球非反应收敛属性。要学习MPG的NASH平衡,在该MPG中,状态空间的大小和/或玩家数量可能非常大,我们建议使用TANDEM所有玩家运行的新的独立政策梯度算法。当梯度评估中没有不确定性时,我们表明我们的算法找到了$ \ epsilon $ -NASH平衡,$ o(1/\ epsilon^2)$迭代复杂性并不明确取决于状态空间大小。如果没有确切的梯度,我们建立$ O(1/\ epsilon^5)$样品复杂度在潜在的无限大型状态空间中,用于利用函数近似的基于样本的算法。此外,我们确定了一类独立的政策梯度算法,这些算法都可以融合零和马尔可夫游戏和马尔可夫合作游戏,并与玩家不喜欢玩的游戏类型。最后,我们提供了计算实验来证实理论发展的优点和有效性。
translated by 谷歌翻译
本文通过离线数据在两人零和马尔可夫游戏中学习NASH Equilibria的进展。具体而言,考虑使用$ S $州的$ \ gamma $ discousped Infinite-Horizo​​n Markov游戏,其中Max-player具有$ $ ACTIVE,而Min-player具有$ B $ Actions。我们提出了一种基于悲观模型的算法,具有伯恩斯坦风格的较低置信界(称为VI-LCB游戏),事实证明,该算法可以找到$ \ varepsilon $ - approximate-approximate nash平衡,带有样品复杂性,不大于$ \ frac {c_ {c_ {c_ {c_ { \ Mathsf {剪切}}}^{\ star} s(a+b)} {(1- \ gamma)^{3} \ varepsilon^{2}} $(最多到某个log factor)。在这里,$ c _ {\ mathsf {剪切}}}^{\ star} $是一些单方面剪接的浓缩系数,反映了可用数据的覆盖范围和分配变化(vis- \`a-vis目标数据),而目标是目标精度$ \ varepsilon $可以是$ \ big(0,\ frac {1} {1- \ gamma} \ big] $的任何值。我们的样本复杂性绑定了先前的艺术,以$ \ min \ {a, b \} $,实现整个$ \ varepsilon $ range的最小值最佳性。我们结果的一个吸引力的功能在于算法简单性,这揭示了降低方差降低和样本拆分的不必要性。
translated by 谷歌翻译
获取一阶遗憾界限 - 遗憾的界限不是作为最坏情况,但有一些衡量给定实例的最佳政策的性能 - 是连续决策的核心问题。虽然这种界限存在于许多设置中,但它们在具有大状态空间的钢筋学习中被证明是难以捉摸的。在这项工作中,我们解决了这个差距,并表明可以将遗憾的缩放作为$ \ mathcal {o}(\ sqrt {v_1 ^ \ star})$中的钢筋学习,即用大状态空间,即线性MDP设置。这里$ v_1 ^ \ star $是最佳政策的价值,$ k $是剧集的数量。我们证明基于最小二乘估计的现有技术不足以获得该结果,而是基于强大的Catoni平均估计器制定一种新的稳健自归一化浓度,其可能具有独立兴趣。
translated by 谷歌翻译