3 citations · 9 across the 31 of their papers we have counts for
9 papers · 1 filter
Rectifying Regression in Reinforcement Learning
Alex Ayoub, David Szepesvári, Alireza Bakhtiari +2
This paper investigates the impact of the loss function in value-based methods for reinforcement learning through an analysis of underlying prediction objectives. We theoretically…
Learning to Reason Efficiently with Discounted Reinforcement Learning
Alex Ayoub, Kavosh Asadi, Dale Schuurmans +2
Large reasoning models (LRMs) often consume excessive tokens, inflating computational cost and latency. More broadly, in goal reaching sequential decision problems we often want to…
Trajectory Data Suffices for Statistically Efficient Policy Evaluation in Fixed-Horizon Offline RL with Linear -Realizability and Concentrability
Volodymyr Tkachuk, Csaba Szepesvári, Xiaoqi Tan
We study finite-horizon offline reinforcement learning (RL) with function approximation for both policy evaluation and policy optimization. Prior work established that statisticall…
Frontier LLMs Still Struggle with Simple Reasoning Tasks
Alan Malek, Jiawei Ge, Nevena Lazic +3
While state-of-the-art large language models (LLMs) demonstrate advanced reasoning capabilities-achieving remarkable performance on challenging competitive math and coding benchmar…
Beyond Statistical Learning: Exact Learning Is Essential for General Intelligence
András György, Tor Lattimore, Nevena Lazić +1
Sound deductive reasoning -- the ability to derive new knowledge from existing facts and rules -- is an indisputably desirable aspect of general intelligence. Despite the major adv…
Rethinking the Global Convergence of Softmax Policy Gradient with Linear Function Approximation: The Case of Multi-Armed Bandits
Max Qiushi Lin, Jincheng Mei, Matin Aghaei +6
Policy gradient (PG) methods have played an essential role in the empirical successes of reinforcement learning. In order to handle large state-action spaces, PG methods are typica…
Ordering-based Conditions for Global Convergence of Policy Gradient Methods
Jincheng Mei, Bo Dai, Alekh Agarwal +3
We prove that, for finite-arm bandits with linear function approximation, the global convergence of policy gradient (PG) methods depends on inter-related properties between the pol…
Balancing optimism and pessimism in offline-to-online learning
Flore Sentenac, Ilbin Lee, Csaba Szepesvari
We consider what we call the offline-to-online learning setting, focusing on stochastic finite-armed bandit problems. In offline-to-online learning, a learner starts with offline d…
Small steps no more: Global convergence of stochastic gradient bandits for arbitrary learning rates
Jincheng Mei, Bo Dai, Alekh Agarwal +4
We provide a new understanding of the stochastic gradient bandit algorithm by showing that it converges to a globally optimal policy almost surely using \emph{any} constant learnin…