English
Related papers

Related papers: Thinker: Learning to Plan and Act

200 papers

Seamlessly interacting with humans or robots is hard because these agents are non-stationary. They update their policy in response to the ego agent's behavior, and the ego agent must anticipate these changes to co-adapt. Inspired by humans,…

Robotics · Computer Science 2020-11-16 Annie Xie , Dylan P. Losey , Ryan Tolsma , Chelsea Finn , Dorsa Sadigh

Training large language models (LLMs) to reason via reinforcement learning (RL) significantly improves their problem-solving capabilities. In agentic settings, existing methods like ReAct prompt LLMs to explicitly plan before every action;…

The model-based reinforcement learning paradigm, which uses planning algorithms and neural network models, has recently achieved unprecedented results in diverse applications, leading to what is now known as deep reinforcement learning.…

Machine Learning · Computer Science 2022-01-11 Tiago Gaspar Oliveira , Arlindo L. Oliveira

AI agents -- systems that combine foundation models with reasoning, planning, memory, and tool use -- are rapidly becoming a practical interface between natural-language intent and real-world computation. This survey synthesizes the…

Artificial Intelligence · Computer Science 2026-01-06 Bin Xu

This paper develops a new approach for estimating an interpretable, relational model of a black-box autonomous agent that can plan and act. Our main contributions are a new paradigm for estimating such models using a minimal query interface…

Artificial Intelligence · Computer Science 2021-04-12 Pulkit Verma , Shashank Rao Marpally , Siddharth Srivastava

While reinforcement learning agents can achieve superhuman performance in many complex tasks, they typically do not become more computationally efficient as they improve. In contrast, humans gradually require less cognitive effort as they…

Artificial Intelligence · Computer Science 2025-10-28 Adrian Orenstein , Jessica Chen , Gwyneth Anne Delos Santos , Bayley Sapara , Michael Bowling

Conventional reinforcement learning (RL) allows an agent to learn policies via environmental rewards only, with a long and slow learning curve, especially at the beginning stage. On the contrary, human learning is usually much faster…

Artificial Intelligence · Computer Science 2019-12-25 Daoming Lyu , Fangkai Yang , Bo Liu , Steven Gustafson

In agent control issues, the idea of combining reinforcement learning and planning has attracted much attention. Two methods focus on micro and macro action respectively. Their advantages would show together if there is a good cooperation…

Artificial Intelligence · Computer Science 2020-03-20 Xuerun Chen

Peer learning is a novel high-level reinforcement learning framework for agents learning in groups. While standard reinforcement learning trains an individual agent in trial-and-error fashion, all on its own, peer learning addresses a…

Machine Learning · Computer Science 2024-05-07 Cedric Derstroff , Mattia Cerrato , Jannis Brugger , Jan Peters , Stefan Kramer

Multi-agent navigation in dynamic environments is of great industrial value when deploying a large scale fleet of robot to real-world applications. This paper proposes a decentralized partially observable multi-agent path planning with…

Robotics · Computer Science 2020-08-03 Zuxin Liu , Baiming Chen , Hongyi Zhou , Guru Koushik , Martial Hebert , Ding Zhao

Many AI systems focus solely on providing solutions or explaining outcomes. However, complex tasks like research and strategic thinking often benefit from a more comprehensive approach to augmenting the thinking process rather than…

Human-Computer Interaction · Computer Science 2024-12-25 Soya Park , Hari Subramonyam , Chinmay Kulkarni

In this paper, we show how a planning algorithm can be used to automatically create and update a Behavior Tree (BT), controlling a robot in a dynamic environment. The planning part of the algorithm is based on the idea of back chaining.…

Robotics · Computer Science 2020-07-16 Michele Colledanchise , Diogo Almeida , Petter Ögren

As complex societal issues continue to emerge, fostering democratic skills like valuing diverse perspectives and collaborative decision-making is increasingly vital in education. In this paper, we propose a Peer Agent (PA) system designed…

Human-Computer Interaction · Computer Science 2025-08-13 Kyuwon Kim , Jaeryeong Hwang , Younseo Lee , Jeanhee Lee , Sung-Eun Kim , Hyo-Jeong So

Model-based Reinforcement Learning approaches have the promise of being sample efficient. Much of the progress in learning dynamics models in RL has been made by learning models via supervised learning. But traditional model-based…

Machine Learning · Computer Science 2019-06-12 Shagun Sodhani , Anirudh Goyal , Tristan Deleu , Yoshua Bengio , Sergey Levine , Jian Tang

Reinforcement learning algorithms describe how an agent can learn an optimal action policy in a sequential decision process, through repeated experience. In a given environment, the agent policy provides him some running and terminal…

Theoretical Economics · Economics 2020-03-24 Arthur Charpentier , Romuald Elie , Carl Remlinger

Reasoning models have recently shown remarkable progress in domains such as math and coding. However, their expert-level abilities in math and coding contrast sharply with their performance in long-horizon, interactive tasks such as web…

Computation and Language · Computer Science 2025-10-13 Xiao Yu , Baolin Peng , Michel Galley , Hao Cheng , Qianhui Wu , Janardhan Kulkarni , Suman Nath , Zhou Yu , Jianfeng Gao

Training a task-completion dialogue agent via reinforcement learning (RL) is costly because it requires many interactions with real users. One common alternative is to use a user simulator. However, a user simulator usually lacks the…

Computation and Language · Computer Science 2018-05-24 Baolin Peng , Xiujun Li , Jianfeng Gao , Jingjing Liu , Kam-Fai Wong , Shang-Yu Su

Reinforcement learning is a powerful technique to train an agent to perform a task. However, an agent that is trained using reinforcement learning is only capable of achieving the single task that is specified via its reward function. Such…

Machine Learning · Computer Science 2018-07-24 Carlos Florensa , David Held , Xinyang Geng , Pieter Abbeel

Evaluating recommender systems remains challenging due to the gap between offline metrics and real user behavior, as well as the scarcity of interaction data. Recent work explores large language model (LLM) agents as synthetic users, yet…

Information Retrieval · Computer Science 2026-01-06 Nicolas Bougie , Gian Maria Marconi , Tony Yip , Narimasa Watanabe

Intelligent robots and machines are becoming pervasive in human populated environments. A desirable capability of these agents is to respond to goal-oriented commands by autonomously constructing task plans. However, such autonomy can add…

Artificial Intelligence · Computer Science 2016-04-14 Yu Zhang , Sarath Sreedharan , Anagha Kulkarni , Tathagata Chakraborti , Hankz Hankui Zhuo , Subbarao Kambhampati