Search Results for author:
Found 13 papers, 0 papers with code
Learning Hidden Markov Models Using Conditional Samples
In this paper, we depart from this setup and consider an interactive access model, in which the algorithm can query for samples from the conditional distributions of the HMMs.
Exponential Hardness of Reinforcement Learning with Linear Function Approximation
The rewards in this game are chosen such that if the learner achieves large reward, then the learner's actions can be used to simulate solving a variant of 3-SAT, where (a) each variable shows up in a bounded number of clauses (b) if an instance has no solutions then it also has no solutions that satisfy more than (1-$\epsilon$)-fraction of clauses.
Do PAC-Learners Learn the Marginal Distribution?
We study a foundational variant of Valiant and Vapnik and Chervonenkis' Probably Approximately Correct (PAC)-Learning in which the adversary is restricted to a known family of marginal distributions $\mathscr{P}$.
Convergence of online $k$-means
We prove asymptotic convergence for a general class of $k$-means algorithms performed over streaming data from a distribution: the centers asymptotically converge to the set of stationary points of the $k$-means cost function.
Computational-Statistical Gaps in Reinforcement Learning
In this work, we make progress on this open problem by presenting the first computational lower bound for RL with linear function approximation: unless NP=RP, no randomized polynomial time algorithm exists for deterministic transition MDPs with a constant number of actions and linear optimal value functions.
Learning what to remember
We consider a lifelong learning scenario in which a learner faces a neverending and arbitrary stream of facts and has to decide which ones to retain in its limited memory.
Realizable Learning is All You Need
The equivalence of realizable and agnostic learnability is a fundamental phenomenon in learning theory.
Bilinear Classes: A Structural Framework for Provable Generalization in RL
The framework incorporates nearly all existing models in which a polynomial sample complexity is achievable, and, notably, also includes new models, such as the Linear $Q^*/V^*$ model in which both the optimal $Q$-function and the optimal $V$-function are linear in some known feature space.
Agnostic $Q$-learning with Function Approximation in Deterministic Systems: Near-Optimal Bounds on Approximation Error and Sample Complexity
The current paper studies the problem of agnostic $Q$-learning with function approximation in deterministic systems where the optimal $Q$-function is approximable by a function in the class $\mathcal{F}$ with approximation error $\delta \ge 0$.
Point Location and Active Learning: Learning Halfspaces Almost Optimally
Given a finite set $X \subset \mathbb{R}^d$ and a binary linear classifier $c: \mathbb{R}^d \to \{0, 1\}$, how many queries of the form $c(x)$ are required to learn the label of every point in $X$?
Agnostic Q-learning with Function Approximation in Deterministic Systems: Tight Bounds on Approximation Error and Sample Complexity
2) In conjunction with the lower bound in [Wen and Van Roy, NIPS 2013], our upper bound suggests that the sample complexity $\widetilde{\Theta}\left(\mathrm{dim}_E\right)$ is tight even in the agnostic setting.
Noise-tolerant, Reliable Active Classification with Comparison Queries
With the explosion of massive, widely available unlabeled data in the past years, finding label and time efficient, robust learning algorithms has become ever more important in theory and in practice.
On the Theory of Policy Gradient Methods: Optimality, Approximation, and Distribution Shift
Policy gradient methods are among the most effective methods in challenging reinforcement learning problems with large state and/or action spaces.
