首页/论文/2011.01337

arXiv 2011.013372020-11-02cs.AIcs.LG

Incorporating Rivalry in Reinforcement Learning for a Competitive Game

Italian Institute of Technology（意大利理工学院）；University of British Columbia（英属哥伦比亚大学）

Pablo Barros, Ana Tanevska, Ozge Yalcin, Alessandra Sciutti

备注：: Accepted at the Pre-registration Workshop @ NeurIPS2020

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

英文摘要相关论文

英文摘要：

Recent advances in reinforcement learning with social agents have allowed us to achieve human-level performance on some interaction tasks. However, most interactive scenarios do not have as end-goal performance alone; instead, the social impact of these agents when interacting with humans is as important and, in most cases, never explored properly. This preregistration study focuses on providing a novel learning mechanism based on a rivalry social impact. Our scenario explored different reinforcement learning-based agents playing a competitive card game against human players. Based on the concept of competitive rivalry, our analysis aims to investigate if we can change the assessment of these agents from a human perspective.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

阅读原文

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

本文内容

英文摘要相关论文

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

继续探索

相关论文

Incorporating Rivalry in Reinforcement Learning for a Competitive Game

Italian Institute of Technology（意大利理工学院）；Simon Fraser University（西蒙弗雷泽大学）

Recent advances in reinforcement learning with social agents have allowed such models to achieve human-level performance on specific interaction tasks. However, most interactive scenarios do not have a version alone as an end goal; instead, the social impact of these agents when interacting with humans is as important and largely unexplored. In this regard, this work proposes a novel reinforcement learning mechanism based on the social impact of rivalry behavior. Our proposed model aggregates objective and social perception mechanisms to derive a rivalry score that is used to modulate the lear…

2022-08-22cs.AI

Hummer：迈向有限竞争偏好数据集

Hummer: Towards Limited Competitive Preference Dataset

Mila, McGill University（蒙特利尔大学Mila实验室）；Peking University（北京大学）；Ant Group（蚂蚁集团）

针对现有偏好数据集对齐目标冲突导致模型易受攻击、下游任务适配难的问题，本文提出对齐维度冲突指标，构建低冲突成对偏好数据集Hummer及细粒度版本，并开发混合采样的奖励模型，可平衡多对齐目标、适配领域微调并降低攻击风险。

2025-10-22cs.AIcs.LG

需要一定监督：通过认知不确定性指标将预言者策略融入强化学习

Some Supervision Required: Incorporating Oracle Policies in Reinforcement Learning via Epistemic Uncertainty Metrics

Coventry University（考文垂大学）；Farama Foundation（法拉马基金会）

针对强化学习随机探索效率低的问题，提出CCGE方法，基于认知不确定性动态引入预言者策略的动作建议，在多种基准任务上提升了样本效率与最终性能，为相关研究提供新思路。

2023-08-21cs.AIcs.LG

ROCM：一致性模型上的RLHF

ROCM: RLHF on consistency models

University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）

本文提出ROCM框架，通过直接奖励优化和$f$-散度分布正则化将RLHF应用于一致性模型，实现高效稳定的单步生成训练，在自动指标和人类评估中优于或媲美策略梯度方法。

2025-03-08cs.AIcs.LG

FiDi-RL: Incorporating Deep Reinforcement Learning with Finite-Difference Policy Search for Efficient Learning of Continuous Control

In recent years significant progress has been made in dealing with challenging problems using reinforcement learning.Despite its great success, reinforcement learning still faces challenge in continuous control tasks. Conventional methods always compute the derivatives of the optimal goal with a costly computation resources, and are inefficient, unstable and lack of robust-ness when dealing with such tasks. Alternatively, derivative-based methods treat the optimization process as a blackbox and show robustness and stability in learning continuous control tasks, but not data efficient in learni…

2020-02-01cs.AIcs.LGstat.ML

价格通胀对通过强化学习智能体实现的算法合谋的影响

Impact of Price Inflation on Algorithmic Collusion Through Reinforcement Learning Agents

Center for Artificial Intelligence (CENIA)（人工智能中心（CENIA））；University of Chile（智利大学）；Advanced Mining Technology Center (AMTC)（先进采矿技术中心（AMTC））

本文研究通胀冲击对强化学习定价智能体合谋行为的影响，发现通胀会促进隐性协调、降低市场竞争性，但智能体缺乏稳健惩罚机制，凸显监管必要性。

2025-04-05cs.GTcs.LG

更多相关论文收起更多论文

用于建模竞争性人类驾驶的博弈论逆强化学习：切入预测研究

Game-Theoretic Inverse Reinforcement Learning for Modeling Competitive Human Driving: A Cut-in Prediction Study

University of Wyoming（怀俄明大学）

本研究提出博弈论逆强化学习（IRL）模型，在highD数据集上验证其在激进切入车道变更预测中，相比基于物理的基准方法，显著提升了高风险场景的预测精确率与召回率，为混合自主环境交互建模提供可靠基础。

2026-08-10cs.LGphysics.soc-ph

竞争性强化学习的后验采样：函数逼近与部分观测

Posterior Sampling for Competitive RL: Function Approximation and Partial Observation

Hong Kong University of Science and Technology（香港科技大学）；New York University（纽约大学）；Peking University（北京大学）；Northwestern University（西北大学）；Yale University（耶鲁大学）

本文针对零和马尔可夫博弈提出基于自博弈与对抗广义eluder系数的模型化后验采样算法，首次在完全及部分可观测场景下实现竞争性强化学习的通用低遗憾学习。

2023-10-30cs.GTcs.LGstat.ML

用于负责任投资组合优化的深度强化学习与均值-方差策略

Deep Reinforcement Learning and Mean-Variance Strategies for Responsible Portfolio Optimization

J.P. Morgan AI Research（摩根大通人工智能研究院）；University College London（伦敦大学学院）

本文研究了将深度强化学习应用于负责任的投资组合优化，通过纳入ESG状态和目标，在财务与ESG责任的加性及乘性效用函数下，表现出与均值-方差方法相媲美的性能。

2024-03-25cs.AI

Concept Learning for Interpretable Multi-Agent Reinforcement Learning

Carnegie Mellon University（卡内基梅隆大学）

Multi-agent robotic systems are increasingly operating in real-world environments in close proximity to humans, yet are largely controlled by policy models with inscrutable deep neural network representations. We introduce a method for incorporating interpretable concepts from a domain expert into models trained through multi-agent reinforcement learning, by requiring the model to first predict such concepts then utilize them for decision making. This allows an expert to both reason about the resulting concept policy models in terms of these high-level concepts at run-time, as well as interven…

2023-02-23cs.AIcs.LGcs.RO

Variational Inference MPC for Bayesian Model-based Reinforcement Learning

Panasonic Corp.（松下公司）；Ritsumeikan Univ.（立命馆大学）

In recent studies on model-based reinforcement learning (MBRL), incorporating uncertainty in forward dynamics is a state-of-the-art strategy to enhance learning performance, making MBRLs competitive to cutting-edge model free methods, especially in simulated robotics tasks. Probabilistic ensembles with trajectory sampling (PETS) is a leading type of MBRL, which employs Bayesian inference to dynamics modeling and model predictive control (MPC) with stochastic optimization via the cross entropy method (CEM). In this paper, we propose a novel extension to the uncertainty-aware MBRL. Our main cont…

2019-10-07cs.LGcs.SYeess.SY

量子纠缠在对抗性博弈中提供竞争优势

Quantum entanglement provides a competitive advantage in adversarial games

CSIRO（联邦科学与工业研究组织）

本研究通过量子-经典混合智能体在Pong对抗性马尔可夫博弈中的实验，发现纠缠量子电路在特征提取和竞争性强化学习中优于可分离电路，表明量子纠缠可作为表示学习的功能资源。

2026-06-03cs.AIcs.LGquant-ph

通过融合知识特征的提示学习增强源代码分类效果

Enhancing Source Code Classification Effectiveness via Prompt Learning Incorporating Knowledge Features

Beijing Institute of Technology（北京理工大学）；Qi-Anxin Technology Group（奇安信科技集团）；Beijing University of Posts and Telecommunications（北京邮电大学）

本文提出CodeClassPrompt，利用提示学习与注意力机制从预训练模型中提取并融合多层知识特征，在降低计算开销的同时提升源代码分类效果。

2024-08-19cs.AIcs.CL

FinePhys：通过显式纳入物理定律实现有效骨骼引导的细粒度人体动作生成

FinePhys: Fine-grained Human Action Generation by Explicitly Incorporating Physical Laws for Effective Skeletal Guidance

Unmanned System Research Institute, Northwestern Polytechnical University, Xi’an, China（无人系统研究院、西北工业大学、西安，中国）；School of Software, Northwestern Polytechnical University, Xi’an, China（软件学院、西北工业大学、西安，中国）；School of Automation, Northwestern Polytechnical University, Xi’an, China（自动化学院、西北工业大学、西安，中国）；School of Astronautics, Northwestern Polytechnical University, Xi’an, China（航天学院、西北工业大学、西安，中国）

针对现有视频生成方法难以合成物理合理的细粒度人体动作的问题，提出融合物理定律的FinePhys框架，通过在线2D姿态估计、上下文学习升维、物理运动重估计及多尺度热图引导扩散，在FineGym数据集上性能优于基线，可生成更自然合理的细粒度动作。

2025-05-19cs.AIcs.CV