影响力指数
论文质量、代表作、近期表现、广度与样本量置信度综合计算
82.14/100
前 1.2%
全站排名 #765
发表论文16 篇
平均评分
年均产出5.3 篇/年
Natasha Jaques
研究方向
multi-agent · reinforcement learning · deep learning · machine learning · RNNs · reinforcement learning from human feedback
10
Improving Human-AI Coordination through Online Adversarial Training and Generative Models
ICLR 2026Poster
通讯12
Learning to summarize user information for personalized reinforcement learning from human feedback
ICLR 2026Poster
通讯21
Generative Adversarial Post-Training Mitigates Reward Hacking in Live Human-AI Music Interaction
ICLR 2026Poster
16
SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning
ICLR 2026Poster
通讯18
Chasing Moving Targets with Online Self-Play Reinforcement Learning for Safer Language Models
ICLR 2026Rejected
通讯20
Modeling Others' Minds as Code
ICLR 2026Poster
15
AutoCode: LLMs as Problem Setters for Competitive Programming
ICLR 2026Poster
17
Deception in Dialogue: Evaluating and Mitigating Deceptive Behavior in Large Language Models
ICLR 2026Rejected
5
DiZCo: Planning Zero-Shot Coordination in World Models
ICLR 2026Withdrawn
通讯12
Towards Understanding Learning from Human Interventions
ICLR 2026Withdrawn
17
Cross-environment Cooperation Enables Zero-shot Multi-agent Coordination
ICML 2025Oral
通讯22
Enhancing Personalized Multi-Turn Dialogue with Curiosity Reward
NeurIPS 2025Poster
通讯21
Consistently Simulating Human Personas with Multi-Turn Reinforcement Learning
NeurIPS 2025Poster
通讯22
InvestESG: A multi-agent reinforcement learning benchmark for studying climate investment as a social dilemma
ICLR 2025Poster
通讯