English
Related papers

Related papers: Expected Eligibility Traces

200 papers

Modern deep learning models are notoriously opaque, which has motivated the development of methods for interpreting how deep models predict. This goal is usually approached with attribution method, which assesses the influence of features…

Machine Learning · Computer Science 2023-03-07 Yiming Ju , Yuanzhe Zhang , Zhao Yang , Zhongtao Jiang , Kang Liu , Jun Zhao

Runtime predictive analyses enhance coverage of traditional dynamic analyses based bug detection techniques by identifying a space of feasible reorderings of the observed execution and determining if any of these witnesses the violation of…

Programming Languages · Computer Science 2024-05-20 Zhendong Ang , Umang Mathur

We study the problem of learning a good set of policies, so that when combined together, they can solve a wide variety of unseen reinforcement learning tasks with no or very little new data. Specifically, we consider the framework of…

Machine Learning · Computer Science 2022-03-16 Safa Alver , Doina Precup

Off-policy learning from multistep returns is crucial for sample-efficient reinforcement learning, particularly in the experience replay setting now commonly used with deep neural networks. Classically, off-policy estimation bias is…

Machine Learning · Computer Science 2021-12-24 Brett Daley , Christopher Amato

Reasoning models improve their problem-solving ability through inference-time scaling, allocating more compute via longer token budgets. Identifying which reasoning traces are likely to succeed remains a key opportunity: reliably predicting…

Artificial Intelligence · Computer Science 2025-10-14 Martina G. Vilas , Safoora Yousefi , Besmira Nushi , Eric Horvitz , Vidhisha Balachandran

Recent work has shown that reinforcement learning agents can develop policies that exploit spurious correlations between rewards and observations. This phenomenon, known as policy confounding, arises because the agent's policy influences…

Machine Learning · Computer Science 2025-06-16 Miguel Suau

Temporal difference (TD) learning is a cornerstone of reinforcement learning. In the average-reward setting, standard TD($\lambda$) is highly sensitive to the choice of step-size and thus requires careful tuning to maintain numerical…

Machine Learning · Statistics 2025-10-08 Hwanwoo Kim , Dongkyu Derek Cho , Eric Laber

We consider the core reinforcement-learning problem of on-policy value function approximation from a batch of trajectory data, and focus on various issues of Temporal Difference (TD) learning and Monte Carlo (MC) policy evaluation. The two…

Scoring systems are commonly seen for platforms in the era of big data. From credit scoring systems in financial services to membership scores in E-commerce shopping platforms, platform managers use such systems to guide users towards the…

Machine Learning · Computer Science 2023-12-20 Xiangguo Sun , Hong Cheng , Hang Dong , Bo Qiao , Si Qin , Qingwei Lin

Abstraction plays an important role in the generalisation of knowledge and skills and is key to sample efficient learning. In this work, we study joint temporal and state abstraction in reinforcement learning, where temporally-extended…

Machine Learning · Computer Science 2022-06-09 Dongge Han , Sebastian Tschiatschek

Automata-conditioned reinforcement learning (RL) has given promising results for learning multi-task policies capable of performing temporally extended objectives given at runtime, done by pretraining and freezing automata embeddings prior…

Machine Learning · Computer Science 2025-05-26 Beyazit Yalcinkaya , Niklas Lauffer , Marcell Vazquez-Chanlatte , Sanjit A. Seshia

Off-policy learning from multistep returns is crucial for sample-efficient reinforcement learning, but counteracting off-policy bias without exacerbating variance is challenging. Classically, off-policy bias is corrected in a per-decision…

Machine Learning · Computer Science 2025-12-23 Brett Daley , Martha White , Christopher Amato , Marlos C. Machado

The ability to transfer knowledge to novel environments and tasks is a sensible desiderata for general learning agents. Despite the apparent promises, transfer in RL is still an open and little exploited research area. In this paper, we…

Machine Learning · Computer Science 2020-10-13 Johan Ferret , Raphaël Marinier , Matthieu Geist , Olivier Pietquin

Happens-before based data race prediction methods infer from a trace of events a partial order to check if one event happens before another event. If two two write events are unordered, they are in a race. We observe that common tracing…

Programming Languages · Computer Science 2019-10-29 Martin Sulzmann , Kai Stadtmüller

The recency heuristic in reinforcement learning is the assumption that stimuli that occurred closer in time to an acquired reward should be more heavily reinforced. The recency heuristic is one of the key assumptions made by TD($\lambda$),…

Machine Learning · Computer Science 2024-08-27 Brett Daley , Marlos C. Machado , Martha White

Sparsity is a common issue in many trajectory datasets, including human mobility data. This issue frequently brings more difficulty to relevant learning tasks, such as trajectory imputation and prediction. Nowadays, little existing work…

Machine Learning · Computer Science 2023-01-13 Kyle K. Qin , Yongli Ren , Wei Shao , Brennan Lake , Filippo Privitera , Flora D. Salim

Transfer learning approaches have shown to significantly improve performance on downstream tasks. However, it is common for prior works to only report where transfer learning was beneficial, ignoring the significant trial-and-error required…

Machine Learning · Computer Science 2022-09-09 Alexander Pugantsov , Richard McCreadie

The predominant approach in reinforcement learning is to assign credit to actions based on the expected return. However, we show that the return may depend on the policy in a way which could lead to excessive variance in value estimation…

Machine Learning · Computer Science 2023-02-07 Hsiao-Ru Pan , Nico Gürtler , Alexander Neitz , Bernhard Schölkopf

Credit assignment is a fundamental problem in reinforcement learning, the problem of measuring an action's influence on future rewards. Explicit credit assignment methods have the potential to boost the performance of RL algorithms on many…

Machine Learning · Computer Science 2022-02-15 Vyacheslav Alipov , Riley Simmons-Edler , Nikita Putintsev , Pavel Kalinin , Dmitry Vetrov

Temporal difference (TD) methods constitute a class of methods for learning predictions in multi-step prediction problems, parameterized by a recency factor lambda. Currently the most important application of these methods is to temporal…

Artificial Intelligence · Computer Science 2008-02-03 P. Cichosz