Search Results for author:
Found 15 papers, 1 papers with code
The Fallacy of Minimizing Local Regret in the Sequential Task Setting
In the realm of Reinforcement Learning (RL), online RL is often conceptualized as an optimization problem, where an algorithm interacts with an unknown environment to minimize cumulative regret.
A Natural Extension To Online Algorithms For Hybrid RL With Limited Coverage
Hybrid Reinforcement Learning (RL), leveraging both online and offline data, has garnered recent interest, yet research on its provable benefits remains sparse.
Sample Efficient Myopic Exploration Through Multitask Reinforcement Learning with Diverse Tasks
Multitask Reinforcement Learning (MTRL) approaches have gained increasing attention for its wide applications in many important Reinforcement Learning (RL) tasks.
Online learning in bandits with predicted context
When the context error is non-vanishing, classical bandit algorithms fail to achieve sublinear regret.
Adaptive Sampling for Discovery
Starting with a large unlabeled dataset, algorithms for ASD adaptively label the points with the goal to maximize the sum of responses.
On the Statistical Benefits of Curriculum Learning
For both settings, we derive the minimax rates for CL with the oracle that provides the optimal curriculum and without the oracle, where the agent has to adaptively learn a good curriculum.
Bandit Algorithms for Precision Medicine
However, the modern precision medicine movement has been enabled by a confluence of events: scientific advances in fields such as genetics and pharmacology, technological advances in mobile devices and wearable sensors, and methodological advances in computing and data sciences.
Safe Exploration by Solving Early Terminated MDP
Safe exploration is crucial for the real-world application of reinforcement learning (RL).
Representation Learning Beyond Linear Prediction Functions
This motivates us to ask whether diversity can be achieved when source tasks and the target task use different prediction function spaces beyond linear functions.
Self-Supervised Continuous Control without Policy Gradient
Despite the remarkable progress made by the policy gradient algorithms in reinforcement learning (RL), sub-optimal policies usually result from the local exploration property of the policy gradient update.
Decision Making Problems with Funnel Structure: A Multi-Task Learning Approach with Application to Email Marketing Campaigns
We analyze both the prediction error and the regret of our algorithms.
TorsionNet: A Reinforcement Learning Approach to Sequential Conformer Search
Molecular geometry prediction of flexible molecules, or conformer search, is a long-standing challenge in computational chemistry.
Zeroth-Order Supervised Policy Improvement
However, PG algorithms rely on exploiting the value function being learned with the first-order update locally, which results in limited sample efficiency.
Reinforcement Learning in Factored MDPs: Oracle-Efficient Algorithms and Tighter Regret Bounds for the Non-Episodic Setting
We study reinforcement learning in non-episodic factored Markov decision processes (FMDPs).
Cautionary Tales on Air-Quality Improvement in Beijing
While this statistic offered some relief for the inhabitants of the capital, we present several analyses based on Beijing's PM2. 5 data of the past 4 years at 36 monitoring sites along with meteorological data of the past 7 years.
