paper-with-me

Papers

Aligning Agents like Large Language Models

2024-06-06 · Adam Jelley, Yuhan Cao, Dave Bignell, Sam Devlin, Tabish Rashid

Training agents to behave as desired in complex 3D environments from high-dimensional sensory information is challenging. Imitation learning from diverse human behavior provides a scalable approach for training an agent with a sensible behavioral prior, but such an agent may not perform the specific behaviors of interest when deployed. To address this issue, we draw an analogy between the undesirable behaviors of imitation learning agents and the unhelpful responses of unaligned large language models (LLMs). We then investigate how the procedure for aligning LLMs can be applied to aligning agents in a 3D environment from pixels. For our analysis, we utilize an academically illustrative part of a modern console game in which the human behavior distribution is multi-modal, but we want our agent to imitate a single mode of this behavior. We demonstrate that we can align our agent to consistently perform the desired mode, while providing insights and advice for successfully applying this approach to training agents. Project webpage at https://adamjelley.github.io/aligning-agents-like-llms .

📄 PDF Abstract BibTeX arXiv:2406.04208

Code (0)

등록된 구현이 없습니다.

Tasks

Imitation Learning

Methods 이 논문이 사용한 방법론

ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…

Similar Papers 제목 키워드 기반

Agent Alignment in Evolving Social Norms

2024-01-09 · ShiMin Li, Tianxiang Sun, Qinyuan Cheng, Xipeng Qiu

Agents based on Large Language Models (LLMs) are increasingly permeating various domains of human production and life, highlighting the importance of aligning them with human values. The current alignment of AI systems p…

Aligning Crowd-sourced Human Feedback for Reinforcement Learning on Code Generation by Large Language Models

2025-03-19 · Man Fai Wong, Chee Wei Tan

This paper studies how AI-assisted programming and large language models (LLM) improve software developers' ability via AI tools (LLM agents) like Github Copilot and Amazon CodeWhisperer, while integrating human feedback…

Bayesian OptimizationCode GenerationLanguage ModelingLanguage Modelling+2

Large Language Models Meet Harry Potter: A Bilingual Dataset for Aligning Dialogue Agents with Characters

2022-11-13 · Nuo Chen, Yan Wang, Haiyun Jiang, Deng Cai 외

In recent years, Dialogue-style Large Language Models (LLMs) such as ChatGPT and GPT4 have demonstrated immense potential in constructing open-domain dialogue agents. However, aligning these agents with specific characte…

Dialogue GenerationIn-Context LearningPersona Dialogue in StoryRetrieval

Beyond Demographics: Aligning Role-playing LLM-based Agents Using Human Belief Networks

2024-06-25 · Yun-Shiuan Chuang, Krirk Nirunwiroj, Zach Studdiford, Agam Goyal 외

Creating human-like large language model (LLM) agents is crucial for faithful social simulation. Having LLMs role-play based on demographic information sometimes improves human likeness but often does not. This study ass…

Language ModelingLanguage ModellingLarge Language Model

Learning to Play Like Humans: A Framework for LLM Adaptation in Interactive Fiction Games

2025-05-18 · Jinming Zhang, Yunfei Long

Interactive Fiction games (IF games) are where players interact through natural language commands. While recent advances in Artificial Intelligence agents have reignited interest in IF games as a domain for studying deci…

Decision Making