paper-with-me

홈 › Papers

Foundation Models for Semantic Novelty in Reinforcement Learning

2022-11-09 · Tarun Gupta, Peter Karkus, Tong Che, Danfei Xu, Marco Pavone

Effectively exploring the environment is a key challenge in reinforcement learning (RL). We address this challenge by defining a novel intrinsic reward based on a foundation model, such as contrastive language image pretraining (CLIP), which can encode a wealth of domain-independent semantic visual-language knowledge about the world. Specifically, our intrinsic reward is defined based on pre-trained CLIP embeddings without any fine-tuning or learning on the target RL task. We demonstrate that CLIP-based intrinsic rewards can drive exploration towards semantically meaningful states and outperform state-of-the-art methods in challenging sparse-reward procedurally-generated environments.

📄 PDF Abstract BibTeX arXiv:2211.04878

Code (0)

등록된 구현이 없습니다.

Tasks

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Methods 이 논문이 사용한 방법론

CLIP Contrastive Language-Image Pre-training (CLIP), consisting of a simplified version of ConVIRT trained from scratch, is an efficient method of image representation learning…

Similar Papers 제목 키워드 기반

Fostering Intrinsic Motivation in Reinforcement Learning with Pretrained Foundation Models

2024-10-09 · Alain Andres, Javier Del Ser

Exploration remains a significant challenge in reinforcement learning, especially in environments where extrinsic rewards are sparse or non-existent. The recent rise of foundation models, such as CLIP, offers an opportun…

reinforcement-learningReinforcement Learning

Foundation World Models for Agents that Learn, Verify, and Adapt Reliably Beyond Static Environments

2026-02-27 · Florent Delgrange arxiv

The next generation of autonomous agents must not only learn efficiently but also act reliably and adapt their behavior in open worlds. Standard approaches typically assume fixed tasks and environments with little or no …

Reinforcement LearningProgram Synthesis

Optimizing Novelty of Top-k Recommendations using Large Language Models and Reinforcement Learning

2024-06-20 · Amit Sharma, Hua Li, Xue Li, Jian Jiao

Given an input query, a recommendation model is trained using user feedback data (e.g., click data) to output a ranked list of items. In real-world systems, besides accuracy, an important consideration for a new model is…

Product RecommendationReinforcement Learning (RL)

Emotion-Gradient Metacognitive RSI (Part I): Theoretical Foundations and Single-Agent Architecture

2025-05-12 · Rintaro Ando

We present the Emotion-Gradient Metacognitive Recursive Self-Improvement (EG-MRSI) framework, a novel architecture that integrates introspective metacognition, emotion-based intrinsic motivation, and recursive self-modif…

Informativeness

Detecting and Adapting to Novelty in Games

2021-06-04 · Xiangyu Peng, Jonathan C. Balloch, Mark O. Riedl

Open-world novelty occurs when the rules of an environment can change abruptly, such as when a game player encounters "house rules". To address open-world novelty, game playing agents must be able to detect when novelty …

Knowledge GraphsModel-based Reinforcement Learningreinforcement-learningReinforcement Learning (RL)