English
Related papers

Related papers: Q-function Decomposition with Intervention Semanti…

200 papers

$Q$-learning is the most fundamental model-free reinforcement learning algorithm. Deployment of $Q$-learning requires approximation of the state-action value function (also known as the $Q$-function). In this work, we provide online random…

Machine Learning · Statistics 2022-04-11 Joosung Min , Lloyd T. Elliott

Deep Q Networks (DQN) have shown remarkable success in various reinforcement learning tasks. However, their reliance on associative learning often leads to the acquisition of spurious correlations, hindering their problem-solving…

Artificial Intelligence · Computer Science 2025-10-28 Elouanes Khelifi , Amir Saki , Usef Faghihi

The $Q$-function is a central quantity in many Reinforcement Learning (RL) algorithms for which RL agents behave following a (soft)-greedy policy w.r.t. to $Q$. It is a powerful tool that allows action selection without a model of the…

Machine Learning · Computer Science 2022-06-01 Nino Vieillard , Marcin Andrychowicz , Anton Raichuk , Olivier Pietquin , Matthieu Geist

Model-based representations recently stand out as a promising framework that embeds latent dynamics information into the representations for downstream off-policy actor-critic learning. It implicitly combines the advantages of both…

Machine Learning · Computer Science 2026-05-13 Jiafei Lyu , Zichuan Lin , Scott Fujimoto , Kai Yang , Yangkun Chen , Saiyong Yang , Zongqing Lu , Deheng Ye

Recently, a variety of new equivariant neural network model architectures have been proposed that generalize better over rotational and reflectional symmetries than standard models. These models are relevant to robotics because many…

Robotics · Computer Science 2021-11-01 Dian Wang , Robin Walters , Xupeng Zhu , Robert Platt

Being able to reason in an environment with a large number of discrete actions is essential to bringing reinforcement learning to a larger class of problems. Recommender systems, industrial plants and language models are only some of the…

Interventions are central to causal learning and reasoning. Yet ultimately an intervention is an abstraction: an agent embedded in a physical environment (perhaps modeled as a Markov decision process) does not typically come equipped with…

Machine Learning · Computer Science 2020-05-28 Benjamin Lansdell

Q-learning and SARSA are foundational reinforcement learning algorithms whose practical success depends critically on step-size calibration. Step-sizes that are too large can cause numerical instability, while step-sizes that are too small…

Machine Learning · Statistics 2026-01-28 Hwanwoo Kim , Eric Laber

When solving long-horizon tasks, it is intriguing to decompose the high-level task into subtasks. Decomposing experiences into reusable subtasks can improve data efficiency, accelerate policy generalization, and in general provide promising…

Machine Learning · Computer Science 2024-10-30 Yiwen Qiu , Yujia Zheng , Kun Zhang

A primary interest in dynamic inverse problems is to identify the underlying temporal behaviour of the system from outside measurements. In this work we consider the case, where the target can be represented by a decomposition of spatial…

Numerical Analysis · Mathematics 2020-06-09 Simon Arridge , Pascal Fernsel , Andreas Hauptmann

Reinforcement learning is a promising paradigm for learning robot control, allowing complex control policies to be learned without requiring a dynamics model. However, even state of the art algorithms can be difficult to tune for optimum…

Machine Learning · Computer Science 2022-10-03 Renata Garcia , Wouter Caarls

Diffusion models have become a popular choice for representing actor policies in behavior cloning and offline reinforcement learning. This is due to their natural ability to optimize an expressive class of distributions over a continuous…

Machine Learning · Computer Science 2025-02-17 Michael Psenka , Alejandro Escontrela , Pieter Abbeel , Yi Ma

Value function factorization has achieved great success in multi-agent reinforcement learning by optimizing joint action-value functions through the maximization of factorized per-agent utilities. To ensure Individual-Global-Maximum…

Multiagent Systems · Computer Science 2023-12-27 Huiqun Li , Hanhan Zhou , Yifei Zou , Dongxiao Yu , Tian Lan

A practical challenge in reinforcement learning are combinatorial action spaces that make planning computationally demanding. For example, in cooperative multi-agent reinforcement learning, a potentially large number of agents jointly…

Off-policy reinforcement learning suffers from extrapolation errors when a learned policy selects actions that are weakly supported in the replay buffer. In this study, we address this issue by drawing an analogy to static friction. From…

Machine Learning · Computer Science 2026-05-12 Hyunwoo Kim , Hyo Kyung Lee

We study the problem of experiment design to learn causal structures from interventional data. We consider an active learning setting in which the experimenter decides to intervene on one of the variables in the system in each step and uses…

Artificial Intelligence · Computer Science 2020-09-09 Amir Amirinezhad , Saber Salehkaleybar , Matin Hashemi

Q-Learning is a fundamental off-policy reinforcement learning (RL) algorithm that has the objective of approximating action-value functions in order to learn optimal policies. Nonetheless, it has difficulties in reconciling bias with…

Machine Learning · Computer Science 2024-11-22 Mahammad Humayoo

Q-shaping is an extension of Q-value initialization and serves as an alternative to reward shaping for incorporating domain knowledge to accelerate agent training, thereby improving sample efficiency by directly shaping Q-values. This…

Artificial Intelligence · Computer Science 2024-10-03 Xiefeng Wu

Value decomposition is widely used in cooperative multi-agent reinforcement learning, however, its implicit credit assignment mechanism is not yet fully understood due to black-box networks. In this work, we study an interpretable value…

Multiagent Systems · Computer Science 2024-01-30 Zichuan Liu , Yuanyang Zhu , Chunlin Chen

Reinforcement learning is a powerful approach for training an optimal policy to solve complex problems in a given system. This project aims to demonstrate the application of reinforcement learning in stochastic process environments with…

Machine Learning · Computer Science 2023-08-08 Kuangheng He