paper-with-me

홈 › Papers

Leveraging class abstraction for commonsense reinforcement learning via residual policy gradient methods

2022-01-28 · Niklas Höpner, Ilaria Tiddi, Herke van Hoof

Enabling reinforcement learning (RL) agents to leverage a knowledge base while learning from experience promises to advance RL in knowledge intensive domains. However, it has proven difficult to leverage knowledge that is not manually tailored to the environment. We propose to use the subclass relationships present in open-source knowledge graphs to abstract away from specific objects. We develop a residual policy gradient method that is able to integrate knowledge across different abstraction levels in the class hierarchy. Our method results in improved sample efficiency and generalisation to unseen objects in commonsense games, but we also investigate failure modes, such as excessive noise in the extracted class knowledge or environments with little class structure.

📄 PDF Abstract BibTeX arXiv:2201.12126

Code (1)

NikeHop/CSRL 공식 구현 pytorch

Tasks

Knowledge GraphsPolicy Gradient Methodsreinforcement-learningReinforcement Learning (RL)

Methods 이 논문이 사용한 방법론

BASE 설명 없음

Similar Papers 제목 키워드 기반

SEA: Evaluating Sketch Abstraction Efficiency via Element-level Commonsense Visual Question Answering

2026-03-30 · Jiho Park, Sieun Choi, Jaeyoon Seo, Minho Sohn 외 arxiv

A sketch is a distilled form of visual abstraction that conveys core concepts through simplified yet purposeful strokes while omitting extraneous detail. Despite its expressive power, quantifying the efficiency of semant…

Visual Question Answering

Efficient Text-based Reinforcement Learning by Jointly Leveraging State and Commonsense Graph Representations

2021-02-22 · Anonymous

Text-based games (TBGs) have emerged as useful benchmarks for evaluating progress at the intersection of grounded language understanding and reinforcement learning (RL). Recent work has proposed the use of external knowl…

Decision MakingGraph Attentionreinforcement-learningReinforcement Learning (RL)+1

Efficient Text-based Reinforcement Learning by Jointly Leveraging State and Commonsense Graph Representations

2021-08-01 · ACL 2021 5 · Keerthiram Murugesan, Mattia Atzeni, Pavan Kapanipathi, Kartik Talamadupula 외

Text-based games (TBGs) have emerged as useful benchmarks for evaluating progress at the intersection of grounded language understanding and reinforcement learning (RL). Recent work has proposed the use of external knowl…

Graph AttentionReinforcement Learning (RL)text-based games

EventLens: Leveraging Event-Aware Pretraining and Cross-modal Linking Enhances Visual Commonsense Reasoning

2024-04-22 · Mingjie Ma, zhihuan yu, Yichao Ma, GuoHui Li

Visual Commonsense Reasoning (VCR) is a cognitive task, challenging models to answer visual questions requiring human commonsense, and to provide rationales explaining why the answers are correct. With emergence of Large…

Visual Commonsense Reasoning

Adaptive state-action abstractions via rate-distortion

2026-06-04 · Fernando E. Rosas arxiv

When learning to walk, infants seem to address a coarse version of the problem first - stay upright, reach the caregiver - and refine it only when further practice at that resolution stops paying off. Reinforcement learn…

Reinforcement Learning