English
Related papers

Related papers: Dynamics-Aware Comparison of Learned Reward Functi…

200 papers

Autonomous agents optimize the reward function we give them. What they don't know is how hard it is for us to design a reward function that actually captures what we want. When designing the reward, we might think of some specific training…

Artificial Intelligence · Computer Science 2020-10-08 Dylan Hadfield-Menell , Smitha Milli , Pieter Abbeel , Stuart Russell , Anca Dragan

Given two sources of evidence about a latent variable, one can combine the information from both by multiplying the likelihoods of each piece of evidence. However, when one or both of the observation models are misspecified, the…

Machine Learning · Computer Science 2021-03-24 Dmitrii Krasheninnikov , Rohin Shah , Herke van Hoof

Learning from Demonstration (LfD) seeks to democratize robotics by enabling non-roboticist end-users to teach robots to perform a task by providing a human demonstration. However, modern LfD techniques, e.g. inverse reinforcement learning…

Robotics · Computer Science 2020-11-24 Letian Chen , Rohan Paleja , Matthew Gombolay

As a robot's operational environment and tasks to perform within it grow in complexity, the explicit specification and balancing of optimization objectives to achieve a preferred behavior profile moves increasingly farther out of reach.…

Robotics · Computer Science 2026-03-10 Yi-Shiuan Tung , Gyanig Kumar , Wei Jiang , Bradley Hayes , Alessandro Roncone

To learn directed behaviors in complex environments, intelligent agents need to optimize objective functions. Various objectives are known for designing artificial agents, including task rewards and intrinsic motivation. However, it is…

Artificial Intelligence · Computer Science 2022-02-15 Danijar Hafner , Pedro A. Ortega , Jimmy Ba , Thomas Parr , Karl Friston , Nicolas Heess

In Agentic Search, trajectory-level outcome rewards fail to quantify the behavioral contributions of individual steps, while existing step-level reward methods typically rely on costly tree sampling. We view world knowledge as a latent…

Artificial Intelligence · Computer Science 2026-05-29 Yuchen Liu , Yingjie Feng , Lixiong Qin , Jiasi Chen , Jianing Yu , Sheng Gao , Sheng Yang , Weiran Xu

We present the ADaptive Adversarial Imitation Learning (ADAIL) algorithm for learning adaptive policies that can be transferred between environments of varying dynamics, by imitating a small number of demonstrations collected from a single…

Machine Learning · Computer Science 2020-08-31 Yiren Lu , Jonathan Tompson

Pedestrian Attribute Recognition (PAR) is a challenging task in intelligent video surveillance. Two key challenges in PAR include complex alignment relations between images and attributes, and imbalanced data distribution. Existing…

Computer Vision and Pattern Recognition · Computer Science 2022-05-30 Zhong Ji , Zhenfei Hu , Yaodong Wang , Shengjia Li

Reinforcement learning provides a powerful and general framework for decision making and control, but its application in practice is often hindered by the need for extensive feature and reward engineering. Deep reinforcement learning…

Machine Learning · Computer Science 2018-08-15 Justin Fu , Katie Luo , Sergey Levine

Designers of AI agents often iterate on the reward function in a trial-and-error process until they get the desired behavior, but this only guarantees good behavior in the training environment. We propose structuring this process as a…

Machine Learning · Computer Science 2023-10-17 Sören Mindermann , Rohin Shah , Adam Gleave , Dylan Hadfield-Menell

In model-based reinforcement learning it is typical to decouple the problems of learning the dynamics model and learning the reward function. However, when the dynamics model is flawed, it may generate erroneous states that would never…

Machine Learning · Computer Science 2018-06-12 Erik Talvitie

Dialogue policy optimization often obtains feedback until task completion in task-oriented dialogue systems. This is insufficient for training intermediate dialogue turns since supervision signals (or rewards) are only provided at the end…

Computation and Language · Computer Science 2020-05-12 Xinting Huang , Jianzhong Qi , Yu Sun , Rui Zhang

Reinforcement learning has been successful across several applications in which agents have to learn to act in environments with sparse feedback. However, despite this empirical success there is still a lack of theoretical understanding of…

Machine Learning · Statistics 2023-11-08 Blake Bordelon , Paul Masset , Henry Kuo , Cengiz Pehlevan

As a robot senses and selects actions, the world keeps changing. This inference delay creates a gap of tens to hundreds of milliseconds between the observed state and the state at execution. In this work, we take the natural generalization…

Robotics · Computer Science 2026-03-25 Aileen Liao , Dong-Ki Kim , Max Olan Smith , Ali-akbar Agha-mohammadi , Shayegan Omidshafiei

How to improve discriminative feature learning is central in classification. Existing works address this problem by explicitly increasing inter-class separability and intra-class similarity, whether by constructing positive and negative…

Machine Learning · Computer Science 2024-08-21 Qingsong Zhao , Yi Wang , Shuguang Dou , Chen Gong , Yin Wang , Cairong Zhao

Preference-based reinforcement learning (PbRL) aligns a robot behavior with human preferences via a reward function learned from binary feedback over agent behaviors. We show that dynamics-aware reward functions improve the sample…

Artificial Intelligence · Computer Science 2024-02-29 Katherine Metcalf , Miguel Sarabia , Natalie Mackraz , Barry-John Theobald

Policy gradient methods are an appealing approach in reinforcement learning because they directly optimize the cumulative reward and can straightforwardly be used with nonlinear function approximators such as neural networks. The two main…

Machine Learning · Computer Science 2018-10-23 John Schulman , Philipp Moritz , Sergey Levine , Michael Jordan , Pieter Abbeel

Training a high-dimensional simulated agent with an under-specified reward function often leads the agent to learn physically infeasible strategies that are ineffective when deployed in the real world. To mitigate these unnatural behaviors,…

Artificial Intelligence · Computer Science 2022-03-30 Alejandro Escontrela , Xue Bin Peng , Wenhao Yu , Tingnan Zhang , Atil Iscen , Ken Goldberg , Pieter Abbeel

In this paper, we introduce MAAD, a novel, sample-efficient on-policy algorithm for Imitation Learning from Observations. MAAD utilizes a surrogate reward signal, which can be derived from various sources such as adversarial games,…

Machine Learning · Computer Science 2025-10-01 João A. Cândido Ramos , Lionel Blondé , Naoya Takeishi , Alexandros Kalousis

We consider off-policy policy evaluation with function approximation (FA) in average-reward MDPs, where the goal is to estimate both the reward rate and the differential value function. For this problem, bootstrapping is necessary and,…

Machine Learning · Computer Science 2022-10-19 Shangtong Zhang , Yi Wan , Richard S. Sutton , Shimon Whiteson