paper-with-me

홈 › Papers

Robot Representation and Reasoning with Knowledge from Reinforcement Learning

2018-09-28 · Keting Lu, Shiqi Zhang, Peter Stone, Xiaoping Chen

Reinforcement learning (RL) agents aim at learning by interacting with an environment, and are not designed for representing or reasoning with declarative knowledge. Knowledge representation and reasoning (KRR) paradigms are strong in declarative KRR tasks, but are ill-equipped to learn from such experiences. In this work, we integrate logical-probabilistic KRR with model-based RL, enabling agents to simultaneously reason with declarative knowledge and learn from interaction experiences. The knowledge from humans and RL is unified and used for dynamically computing task-specific planning models under potentially new environments. Experiments were conducted using a mobile robot working on dialog, navigation, and delivery tasks. Results show significant improvements, in comparison to existing model-based RL methods.

📄 PDF Abstract BibTeX arXiv:1809.11074

Code (0)

등록된 구현이 없습니다.

Tasks

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

Learning and Reasoning for Robot Dialog and Navigation Tasks

2020-05-20 · SIGDIAL (ACL) 2020 7 · Keting Lu, Shiqi Zhang, Peter Stone, Xiaoping Chen

Reinforcement learning and probabilistic reasoning algorithms aim at learning from interaction experiences and reasoning with probabilistic contextual knowledge respectively. In this research, we develop algorithms for r…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Vision-Language Models Provide Promptable Representations for Reinforcement Learning

2024-02-05 · William Chen, Oier Mees, Aviral Kumar, Sergey Levine

Humans can quickly learn new behaviors by leveraging background world knowledge. In contrast, agents trained with reinforcement learning (RL) typically learn behaviors from scratch. We thus propose a novel approach that …

Common Sense ReasoningInstruction FollowingMinecraftreinforcement-learning+4

Reasoning for Moving Blocks Problem: Formal Representation and Implementation

2013-07-28 · P. A. Wałȩga

The combined approach of the Qualitative Reasoning and Probabilistic Functions for the knowledge representation is proposed. The method aims at represent uncertain, qualitative knowledge that is essential for the moving …

State Representations as Incentives for Reinforcement Learning Agents: A Sim2Real Analysis on Robotic Grasping

2023-09-21 · Panagiotis Petropoulakis, Ludwig Gräf, Mohammadhossein Malmir, Josip Josifovski 외

Choosing an appropriate representation of the environment for the underlying decision-making process of the reinforcement learning agent is not always straightforward. The state representation should be inclusive enough …

Decision Makingreinforcement-learningReinforcement LearningRepresentation Learning+1

A Knowledge Driven Approach to Adaptive Assistance Using Preference Reasoning and Explanation

2020-12-05 · Jason R. Wilson, Leilani Gilpin, Irina Rabkina

There is a need for socially assistive robots (SARs) to provide transparency in their behavior by explaining their reasoning. Additionally, the reasoning and explanation should represent the user's preferences and goals.…