English
Related papers

Related papers: Neural Reward Machines

200 papers

Unlike the standard Reinforcement Learning (RL) model, many real-world tasks are non-Markovian, whose rewards are predicated on state history rather than solely on the current state. Solving a non-Markovian task, frequently applied in…

Machine Learning · Computer Science 2023-10-19 Ruixuan Miao , Xu Lu , Cong Tian , Bin Yu , Zhenhua Duan

Reinforcement learning (RL) is a central problem in artificial intelligence. This problem consists of defining artificial agents that can learn optimal behaviour by interacting with an environment -- where the optimal behaviour is defined…

The commonly used Reinforcement Learning (RL) model, MDPs (Markov Decision Processes), has a basic premise that rewards depend on the current state and action only. However, many real-world tasks are non-Markovian, which has long-term…

Machine Learning · Computer Science 2024-12-18 Ruixuan Miao , Xu Lu , Cong Tian , Bin Yu , Zhenhua Duan

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

In multi-agent reinforcement learning (MARL), it is challenging for a collection of agents to learn complex temporally extended tasks. The difficulties lie in computational complexity and how to learn the high-level ideas behind reward…

Multiagent Systems · Computer Science 2021-10-04 Jueming Hu , Zhe Xu , Weichang Wang , Guannan Qu , Yutian Pang , Yongming Liu

Recent studies show that deep reinforcement learning (DRL) agents tend to overfit to the task on which they were trained and fail to adapt to minor environment changes. To expedite learning when transferring to unseen tasks, we propose a…

Artificial Intelligence · Computer Science 2024-02-22 Guy Azran , Mohamad H. Danesh , Stefano V. Albrecht , Sarah Keren

Reinforcement learning (RL) is a powerful approach for training agents to perform tasks, but designing an appropriate reward mechanism is critical to its success. However, in many cases, the complexity of the learning objectives goes beyond…

Machine Learning · Computer Science 2023-08-16 Ernst Moritz Hahn , Mateo Perez , Sven Schewe , Fabio Somenzi , Ashutosh Trivedi , Dominik Wojtczak

Recent progress in deep reinforcement learning (DRL) can be largely attributed to the use of neural networks. However, this black-box approach fails to explain the learned policy in a human understandable way. To address this challenge and…

Artificial Intelligence · Computer Science 2021-03-17 Zhihao Ma , Yuzheng Zhuang , Paul Weng , Hankz Hankui Zhuo , Dong Li , Wulong Liu , Jianye Hao

Current learning models often struggle with human-like systematic generalization, particularly in learning compositional rules from limited data and extrapolating them to novel combinations. We introduce the Neural-Symbolic Recursive…

Machine Learning · Computer Science 2024-04-30 Qing Li , Yixin Zhu , Yitao Liang , Ying Nian Wu , Song-Chun Zhu , Siyuan Huang

This paper presents a novel approach to Multi-Agent Reinforcement Learning (MARL) that combines cooperative task decomposition with the learning of reward machines (RMs) encoding the structure of the sub-tasks. The proposed method helps…

Artificial Intelligence · Computer Science 2025-02-17 Leo Ardon , Daniel Furelos-Blanco , Alessandra Russo

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

Large Language Models (LLMs) have shown remarkable reasoning performance but struggle with multi-step deductive reasoning involving a series of rule application steps, especially when rules are presented non-sequentially. Our preliminary…

Computation and Language · Computer Science 2024-08-27 Siyuan Wang , Zhongyu Wei , Yejin Choi , Xiang Ren

Deep reinforcement learning (RL) methods often require many trials before convergence, and no direct interpretability of trained policies is provided. In order to achieve fast convergence and interpretability for the policy in RL, we…

Continuously learning new tasks using high-level ideas or knowledge is a key capability of humans. In this paper, we propose Lifelong reinforcement learning with Sequential linear temporal logic formulas and Reward Machines (LSRM), which…

Artificial Intelligence · Computer Science 2021-11-19 Xuejing Zheng , Chao Yu , Chen Chen , Jianye Hao , Hankz Hankui Zhuo

We propose the Neural Logic Machine (NLM), a neural-symbolic architecture for both inductive learning and logic reasoning. NLMs exploit the power of both neural networks---as function approximators, and logic programming---as a symbolic…

Artificial Intelligence · Computer Science 2019-04-29 Honghua Dong , Jiayuan Mao , Tian Lin , Chong Wang , Lihong Li , Denny Zhou

Statistical Relational Learning (SRL) models have attracted significant attention due to their ability to model complex data while handling uncertainty. However, most of these models have been limited to discrete domains due to their…

Machine Learning · Computer Science 2021-10-20 Yuqiao Chen , Sriraam Natarajan , Nicholas Ruozzi

Large Language Models (LLMs) exhibit persistent logical failures in complex reasoning due to the lack of an internal axiomatic framework. We propose Mathesis, a neuro-symbolic architecture that encodes mathematical states as higher-order…

Artificial Intelligence · Computer Science 2026-01-05 Keqin Xie

Reinforcement learning (RL) is a technique to learn the control policy for an agent that interacts with a stochastic environment. In any given state, the agent takes some action, and the environment determines the probability distribution…

Machine Learning · Computer Science 2021-07-30 Gaurav Gupta , Chenzhong Yin , Jyotirmoy V. Deshmukh , Paul Bogdan

Reward models play a critical role in guiding large language models toward outputs that align with human expectations. However, an open challenge remains in effectively utilizing test-time compute to enhance reward model performance. In…

Computation and Language · Computer Science 2025-05-21 Jiaxin Guo , Zewen Chi , Li Dong , Qingxiu Dong , Xun Wu , Shaohan Huang , Furu Wei

The area of Neurosymbolic Artificial Intelligence (Neurosymbolic AI) is rapidly developing and has become a popular research topic, encompassing sub-fields such as Neurosymbolic Deep Learning (Neurosymbolic DL) and Neurosymbolic…

Artificial Intelligence · Computer Science 2023-09-06 K. Acharya , W. Raza , C. M. J. M. Dourado , A. Velasquez , H. Song