English
Related papers

Related papers: A compact, hierarchical Q-function decomposition

200 papers

Temporal credit assignment in reinforcement learning has long been a central challenge. Inspired by the multi-timescale encoding of the dopamine system in neurobiology, recent research has sought to introduce multiple discount factors into…

Machine Learning · Computer Science 2026-05-25 Jing Sun

In this work, we propose a novel cross Q-learning algorithm, aim at alleviating the well-known overestimation problem in value-based reinforcement learning methods, particularly in the deep Q-networks where the overestimation is exaggerated…

Artificial Intelligence · Computer Science 2020-09-30 Xing Wang , Alexander Vinel

In representation learning, a disentangled representation is highly desirable as it encodes generative factors of data in a separable and compact pattern. Researchers have advocated leveraging disentangled representations to complete…

Computer Vision and Pattern Recognition · Computer Science 2024-03-04 Ruiqian Nai , Zixin Wen , Ji Li , Yuanzhi Li , Yang Gao

Reinforcement learning algorithms typically necessitate extensive exploration of the state space to find optimal policies. However, in safety-critical applications, the risks associated with such exploration can lead to catastrophic…

Machine Learning · Computer Science 2025-02-28 Kaustubh Mani , Vincent Mai , Charlie Gauthier , Annie Chen , Samer Nashed , Liam Paull

Learning from off-policy data is essential for sample-efficient reinforcement learning. In the present work, we build on the insight that the advantage function can be understood as the causal effect of an action on the return, and show…

Machine Learning · Computer Science 2024-02-21 Hsiao-Ru Pan , Bernhard Schölkopf

Score-function based methods for policy learning, such as REINFORCE and PPO, have delivered strong results in game-playing and robotics, yet their high variance often undermines training stability. Using pathwise policy gradients, i.e.…

Early-exiting neural networks enable adaptive inference by allowing inputs to exit at intermediate classifiers, reducing computation for easy samples while maintaining high accuracy. In practice, exits can be trained sequentially by…

Machine Learning · Computer Science 2026-05-08 Alaa Zniber , Ouassim Karrakchou , Mounir Ghogho

To accumulate knowledge and improve its policy of behaviour, a reinforcement learning agent can learn `off-policy' about policies that differ from the policy used to generate its experience. This is important to learn counterfactuals, or…

Machine Learning · Computer Science 2022-02-03 Simon Schmitt , John Shawe-Taylor , Hado van Hasselt

One approach for improving sample efficiency in cooperative multi-agent learning is to decompose overall tasks into sub-tasks that can be assigned to individual agents. We study this problem in the context of reward machines: symbolic tasks…

Multiagent Systems · Computer Science 2025-02-20 Ameesh Shah , Niklas Lauffer , Thomas Chen , Nikhil Pitta , Sanjit A. Seshia

Reinforcement learning (RL) methods usually treat reward functions as black boxes. As such, these methods must extensively interact with the environment in order to discover rewards and optimal policies. In most RL applications, however,…

Machine Learning · Computer Science 2022-01-19 Rodrigo Toro Icarte , Toryn Q. Klassen , Richard Valenzano , Sheila A. McIlraith

In safety-critical RL settings, the inclusion of an additional cost function is often favoured over the arduous task of modifying the reward function to ensure the agent's safe behaviour. However, designing or evaluating such a cost…

Artificial Intelligence · Computer Science 2025-01-14 Shashank Reddy Chirra , Pradeep Varakantham , Praveen Paruchuri

One question central to Reinforcement Learning is how to learn a feature representation that supports algorithm scaling and re-use of learned information from different tasks. Successor Features approach this problem by learning a feature…

Artificial Intelligence · Computer Science 2017-08-02 Lucas Lehnert , Stefanie Tellex , Michael L. Littman

Sensory representation is typically understood through a hierarchical-causal framework where progressively abstract features are extracted sequentially. However, this causal view fails to explain misrepresentation, a phenomenon better…

Neurons and Cognition · Quantitative Biology 2025-10-15 Shunsuke Onoo , Yoshihiro Nagano , Yukiyasu Kamitani

In this article, we propose a novel algorithm for deep reinforcement learning named Expert Q-learning. Expert Q-learning is inspired by Dueling Q-learning and aims at incorporating semi-supervised learning into reinforcement learning…

Machine Learning · Computer Science 2024-06-26 Li Meng , Anis Yazidi , Morten Goodwin , Paal Engelstad

One of the key challenges in applying reinforcement learning to real-life problems is that the amount of train-and-error required to learn a good policy increases drastically as the task becomes complex. One potential solution to this…

Machine Learning · Computer Science 2018-06-29 Kazeto Yamamoto , Takashi Onishi , Yoshimasa Tsuruoka

Efficient exploration is one of the most important issues in deep reinforcement learning. To address this issue, recent methods consider the value function parameters as random variables, and resort variational inference to approximate the…

Machine Learning · Computer Science 2020-11-04 Haotian Zhang , Yuhao Wang , Jianyong Sun , Zongben Xu

Reward machines (RMs) are a recent formalism for representing the reward function of a reinforcement learning task through a finite-state machine whose edges encode subgoals of the task using high-level events. The structure of RMs enables…

Machine Learning · Computer Science 2023-06-06 Daniel Furelos-Blanco , Mark Law , Anders Jonsson , Krysia Broda , Alessandra Russo

Q-learning is widely recognized as an effective approach for synthesizing controllers to achieve specific goals. However, handling challenges posed by continuous state-action spaces remains an ongoing research focus. This paper presents a…

Systems and Control · Electrical Eng. & Systems 2024-06-07 Sadek Belamfedel Alaoui , Adnane Saoud

Popular Maximum Entropy Inverse Reinforcement Learning approaches require the computation of expected state visitation frequencies for the optimal policy under an estimate of the reward function. This usually requires intermediate value…

Machine Learning · Computer Science 2020-08-05 Gabriel Kalweit , Maria Huegle , Moritz Werling , Joschka Boedecker

Q-learning provides a standard reinforcement learning framework for studying cooperation by specifying how agents update action values from repeated local interactions outcomes. Although previous work has shown that reputation can promote…

Physics and Society · Physics 2026-02-03 Chunpeng Du , Zongyang Li , Yali Zhang , Yikang Lu , Attila Szolnoki