Search Results for author:
Found 28 papers, 4 papers with code
OpenAI o1 System Card
The o1 model series is trained with large-scale reinforcement learning to reason using chain of thought.
Efficient Exploration for LLMs
We present evidence of substantial benefit from efficient exploration in gathering human feedback to improve large language models.
Efficient Online Learning with Offline Datasets for Infinite Horizon MDPs: A Bayesian Approach
In this paper, we study the problem of efficient online reinforcement learning in the infinite horizon setting when there is an offline dataset to start with.
Bridging Imitation and Online Reinforcement Learning: An Optimistic Tale
We first propose an Informed Posterior Sampling-based RL (iPSRL) algorithm that uses the offline dataset, and information about the expert's behavioral policy used to generate the offline dataset.
Leveraging Demonstrations to Improve Online Learning: Quality Matters
This offers insight into how pretraining can greatly improve online performance and how the degree of improvement increases with the expert's competence level.
Sample Efficient Deep Reinforcement Learning via Local Planning
One useful property of simulators is that it is typically easy to reset the environment to a previously observed state.
Regret Bounds for Information-Directed Reinforcement Learning
Information-directed sampling (IDS) has revealed its potential as a data-efficient algorithm for reinforcement learning (RL).
Contextual Information-Directed Sampling
Information-directed sampling (IDS) has recently demonstrated its potential as a data-efficient reinforcement learning algorithm.
Interacting Contour Stochastic Gradient Langevin Dynamics
We propose an interacting contour stochastic gradient Langevin dynamics (ICSGLD) sampler, an embarrassingly parallel multiple-chain contour stochastic gradient Langevin dynamics (CSGLD) sampler with efficient interactions.
The Neural Testbed: Evaluating Joint Predictions
Predictive distributions quantify uncertainties ignored by point estimates.
Evaluating Predictive Distributions: Does Bayesian Deep Learning Work?
This paper introduces \textit{The Neural Testbed}, which provides tools for the systematic evaluation of agents that generate such predictions.
Efficient Local Planning with Linear Function Approximation
Under the assumption that the Q-functions of all policies are linear in known features of the state-action pairs, we show that our algorithms have polynomial query and computational costs in the dimension of the features, the effective planning horizon, and the targeted sub-optimality, while these costs are independent of the size of the state space.
Bandit Phase Retrieval
We study a bandit version of phase retrieval where the learner chooses actions $(A_t)_{t=1}^n$ in the $d$-dimensional unit ball and the expected reward is $\langle A_t, \theta_\star\rangle^2$ where $\theta_\star \in \mathbb R^d$ is an unknown parameter vector.
Information Directed Sampling for Sparse Linear Bandits
Stochastic sparse linear bandits offer a practical model for high-dimensional online decision-making problems and have a rich information-regret structure.
Optimization Issues in KL-Constrained Approximate Policy Iteration
We compare the use of KL divergence as a constraint vs. as a regularizer, and point out several optimization issues with the widely-used constrained approach.
Bootstrapping Fitted Q-Evaluation for Off-Policy Inference
Bootstrapping provides a flexible and effective approach for assessing the quality of batch reinforcement learning, yet its theoretical property is less understood.
High-Dimensional Sparse Linear Bandits
Stochastic linear bandits with high-dimensional sparse features are a practical model for a variety of domains, including personalized medicine and online advertising.
Sparse Feature Selection Makes Batch Reinforcement Learning More Sample Efficient
To evaluate a new target policy, we analyze a Lasso fitted Q-evaluation method and establish a finite-sample error bound that has no polynomial dependence on the ambient dimension.
Online Sparse Reinforcement Learning
First, we provide a lower bound showing that linear regret is generally unavoidable in this case, even if there exists a policy that collects well-conditioned data.
Stochastic Low-rank Tensor Bandits for Multi-dimensional Online Decision Making
We consider two settings, tensor bandits without context and tensor bandits with context.
Residual Bootstrap Exploration for Bandit Algorithms
In this paper, we propose a novel perturbation-based exploration method in bandit algorithms with bounded or unbounded rewards, called residual bootstrap exploration (\texttt{ReBoot}).
Adaptive Approximate Policy Iteration
This is an improvement over the best existing bound of $\tilde{O}(T^{3/4})$ for the average-reward case with function approximation.
Adaptive Exploration in Linear Contextual Bandit
Contextual bandits serve as a fundamental model for many sequential decision making tasks.
Bootstrapping Upper Confidence Bound
Upper Confidence Bound (UCB) method is arguably the most celebrated one used in online decision making with partial information feedback.
Sparse Tensor Additive Regression
Tensors are becoming prevalent in modern applications such as medical imaging and digital marketing.
Sparse and Low-rank Tensor Estimation via Cubic Sketchings
In this paper, we propose a general framework for sparse and low-rank tensor estimation from cubic sketchings.
Simultaneous Clustering and Estimation of Heterogeneous Graphical Models
We consider joint estimation of multiple graphical models arising from heterogeneous and high-dimensional observations.
