English
Related papers

Related papers: Reconciling Rewards with Predictive State Represen…

200 papers

Constrained Markov decision processes (CMDPs) model scenarios of sequential decision making with multiple objectives that are increasingly important in many applications. However, the model is often unknown and must be learned online while…

Machine Learning · Computer Science 2023-01-30 Krishna C Kalagarla , Rahul Jain , Pierluigi Nuzzo

We propose a new approach to value function approximation which combines linear temporal difference reinforcement learning with subspace identification. In practical applications, reinforcement learning (RL) is complicated by the fact that…

Machine Learning · Computer Science 2015-03-17 Byron Boots , Geoffrey J. Gordon

The increasing trend to integrate neural networks and conventional software components in safety-critical settings calls for methodologies for their formal modelling, verification and correct-by-construction policy synthesis. We introduce…

Systems and Control · Electrical Eng. & Systems 2024-08-08 Rui Yan , Gabriel Santos , Gethin Norman , David Parker , Marta Kwiatkowska

Process reward models (PRMs) allow for fine-grained credit assignment in reinforcement learning (RL), and seemingly contrast with outcome reward models (ORMs), which assign a single reward to an entire trajectory. However, we provide…

Machine Learning · Computer Science 2026-05-29 Michael Sullivan , Alexander Koller

Techniques that learn improved representations via offline data or self-supervised objectives have shown impressive results in traditional reinforcement learning (RL). Nevertheless, it is unclear how improved representation learning can…

Computation and Language · Computer Science 2024-10-25 Vaskar Nath , Dylan Slack , Jeff Da , Yuntao Ma , Hugh Zhang , Spencer Whitehead , Sean Hendryx

Preference-based Reinforcement Learning (PbRL) provides a way to learn high-performance policies in environments where the reward signal is hard to specify, avoiding heuristic and time-consuming reward design. However, PbRL can suffer from…

Machine Learning · Computer Science 2025-07-02 Chenyang Cao , Miguel Rogel-García , Mohamed Nabail , Xueqian Wang , Nicholas Rhinehart

Generalization in partially observed markov decision processes (POMDPs) is critical for successful applications of visual reinforcement learning (VRL) in real scenarios. A widely used idea is to learn task-relevant representations that…

Machine Learning · Computer Science 2023-02-21 Jie Wang , Rui Yang , Zijie Geng , Zhihao Shi , Mingxuan Ye , Qi Zhou , Shuiwang Ji , Bin Li , Yongdong Zhang , Feng Wu

Strictly proper scoring rules (SPSR) are incentive compatible for eliciting information about random variables from strategic agents when the principal can reward agents after the realization of the random variables. They also quantify the…

Computer Science and Game Theory · Computer Science 2020-06-09 Yang Liu , Juntao Wang , Yiling Chen

In offline reinforcement learning-based recommender systems (RLRS), learning effective state representations is crucial for capturing user preferences that directly impact long-term rewards. However, raw state representations often contain…

Information Retrieval · Computer Science 2025-02-05 Siyu Wang , Xiaocong Chen , Lina Yao

We propose a framework for modeling and estimating the state of controlled dynamical systems, where an agent can affect the system through actions and receives partial observations. Based on this framework, we propose the Predictive State…

Machine Learning · Statistics 2018-03-02 Ahmed Hefny , Carlton Downey , Geoffrey J. Gordon

State of the art methods for target tracking with sensor management (or controlled sensing) are model-based and are obtained through solutions to Partially Observable Markov Decision Process (POMDP) formulations. In this paper a…

Signal Processing · Electrical Eng. & Systems 2024-07-22 Adarsh M. Subramaniam , Argyrios Gerogiannis , James Z. Hare , Venugopal V. Veeravalli

In robust Markov decision processes (RMDPs), it is assumed that the reward and the transition dynamics lie in a given uncertainty set. By targeting maximal return under the most adversarial model from that set, RMDPs address performance…

Machine Learning · Computer Science 2024-02-13 Uri Gadot , Esther Derman , Navdeep Kumar , Maxence Mohamed Elfatihi , Kfir Levy , Shie Mannor

Preference-based Reinforcement Learning (PbRL) replaces reward values in traditional reinforcement learning by preferences to better elicit human opinion on the target objective, especially when numerical reward values are hard to design or…

Machine Learning · Computer Science 2020-10-27 Yichong Xu , Ruosong Wang , Lin F. Yang , Aarti Singh , Artur Dubrawski

Mathematical reasoning in large language models has improved substantially with reinforcement learning using verifiable rewards, where final answers can be checked automatically and converted into reliable training signals. Most such…

Machine Learning · Computer Science 2026-04-06 Mohammad Rezaei , Jens Lehmann , Sahar Vahdati

Reward models (RMs) play a crucial role in aligning large language models (LLMs) with human preferences and enhancing reasoning quality. Traditionally, RMs are trained to rank candidate outputs based on their correctness and coherence.…

Machine Learning · Computer Science 2025-02-21 Yuhui Xu , Hanze Dong , Lei Wang , Caiming Xiong , Junnan Li

We study multi-objective reinforcement learning with nonlinear preferences over trajectories. That is, we maximize the expected value of a nonlinear function over accumulated rewards (expected scalarized return or ESR) in a multi-objective…

Machine Learning · Computer Science 2025-02-19 Nianli Peng , Muhang Tian , Brandon Fain

In this paper, we tackle the problem of transferring policy from multiple partially observable source environments to a partially observable target environment modeled as predictive state representation. This is an entirely new approach…

Machine Learning · Computer Science 2017-02-09 Sri Ramana Sekharan , Ramkumar Natarajan , Siddharthan Rajasekaran

Partially observable Markov decision processes (POMDPs) rely on the key assumption that probability distributions are precisely known. Robust POMDPs (RPOMDPs) alleviate this concern by defining imprecise probabilities, referred to as…

Artificial Intelligence · Computer Science 2024-07-30 Eline M. Bovy , Marnix Suilen , Sebastian Junges , Nils Jansen

Planning plays an important role in the broad class of decision theory. Planning has drawn much attention in recent work in the robotics and sequential decision making areas. Recently, Reinforcement Learning (RL), as an agent-environment…

Artificial Intelligence · Computer Science 2016-08-18 Kamyar Azizzadenesheli , Alessandro Lazaric , Animashree Anandkumar

In recent years, the successor representation (SR) has attracted increasing attention in reinforcement learning (RL), and it has been used to address some of its key challenges, such as exploration, credit assignment, and generalization.…

Machine Learning · Computer Science 2026-02-03 Hon Tik Tse , Siddarth Chandrasekar , Marlos C. Machado