PaperHub

Jakob Nicolaus Foerster

~Jakob_Nicolaus_Foerster1

47
论文总数
23.5
年均投稿
5.8
平均评分
接收情况30/47
会议分布
ICLR
27
NeurIPS
16
ICML
3
COLM
1

发表论文 (47 篇)

202528 篇

7.8
4

AgentBreeder: Mitigating the AI Safety Risks of Multi-Agent Scaffolds via Self-Improvement

NeurIPS 2025Spotlight
6.0
3

The Decrypto Benchmark for Multi-Agent Reasoning and Theory of Mind

ICLR 2025Rejected
5.5
4

TICKing All the Boxes: Generated Checklists Improve LLM Evaluation and Generation

ICLR 2025Rejected
5.0
4

Learning Loss Landscapes in Preference Optimization

ICLR 2025Rejected
6.8
4

Meta-Learning Objectives for Preference Optimization

NeurIPS 2025Poster
5.0
5

The Complexity Dynamics of Grokking

ICLR 2025Rejected
7.8
4

Improving Regret Approximation for Unsupervised Dynamic Environment Generation

NeurIPS 2025Poster
8.0
4

Kinetix: Investigating the Training of General Agents through Open-Ended Physics-Based Control Tasks

ICLR 2025Oral
3.0
4

Do Symbolic or Black-Box Representations Generalise Better In Learned Optimisation?

ICLR 2025Rejected
4.8
4

CURATe: Benchmarking Personalised Alignment of Conversational AI Assistants

ICLR 2025Rejected
6.3
4

Expected Return Symmetries

ICLR 2025Poster
6.8
4

LILO: Learning to Reason at the Frontier of Learnability

NeurIPS 2025Poster
4.3
4

Beyond the Boundaries of Proximal Policy Optimization

ICLR 2025Rejected
6.8
4

Imagined Autocurricula

NeurIPS 2025Poster
8.2
4

A Clean Slate for Offline Reinforcement Learning

NeurIPS 2025Oral
5.5
4

Towards Learning to Reason at Pre-Training Scale

ICLR 2025Rejected
7.5
4

Simplifying Deep Temporal Difference Learning

ICLR 2025Spotlight
5.3
3

OvercookedV2: Rethinking Overcooked for Zero-Shot Coordination

ICLR 2025Poster
4.3
4

Source2Synth: Synthetic Data Generation and Curation Grounded in Real Data Sources

ICLR 2025Rejected
3.3
3

LOB-Bench: Benchmarking Generative AI for Finance - with an Application to Limit Order Book Markets

ICLR 2025Rejected
4.8
4

Ad-Hoc Human-AI Coordination Challenge

ICLR 2025Rejected
4.2
5

Investigating Online RL in World Models

ICLR 2025Rejected
5.5
4

Ad-Hoc Human-AI Coordination Challenge

ICML 2025Spotlight
6.3
3

LOB-Bench: Benchmarking Generative AI for Finance - an Application to Limit Order Book Data

ICML 2025Poster
5.5
4

ADIOS: Antibody Development via Opponent Shaping

ICML 2025Poster
6.3
4

BALROG: Benchmarking Agentic LLM and VLM Reasoning On Games

ICLR 2025Poster
5.7
3

MLGym: A New Framework and Benchmark for Advancing AI Research Agents

COLM 2025Poster
7.3
4

AI Research Agents for Machine Learning: Search, Exploration, and Generalization in MLE-bench

NeurIPS 2025Spotlight

202419 篇

3.7
6

DITTO: Offline Imitation Learning with World Models

ICLR 2024Rejected
6.0
4

Learning Multi-Agent Communication with Contrastive Learning

ICLR 2024Poster
6.5
4

The Edge-of-Reach Problem in Offline Model-Based Reinforcement Learning

NeurIPS 2024Poster
7.3
3

Illusory Attacks: Information-theoretic detectability matters in adversarial attacks

ICLR 2024Spotlight
7.0
5

Select to Perfect: Imitating desired behavior from large multi-agent data

ICLR 2024Poster
3.0
4

Discovering Minimal Reinforcement Learning Environments

ICLR 2024Rejected
6.5
4

Discovering Preference Optimization Algorithms with and for Large Language Models

NeurIPS 2024Poster
3.8
4

EvIL: Evolution Strategies for Generalisable Imitation Learning

ICLR 2024Rejected
5.5
4

ReLU to the Rescue: Improve Your On-Policy Actor-Critic with Positive Advantages

ICLR 2024Rejected
6.7
3

Behaviour Distillation

ICLR 2024Poster
6.5
4

Artificial Generational Intelligence: Cultural Accumulation in Reinforcement Learning

NeurIPS 2024Poster
4.7
3

Computing Low-Entropy Couplings for Large-Support Distributions

ICLR 2024Rejected
7.3
4

Can Learned Optimization Make Reinforcement Learning Less Difficult?

NeurIPS 2024Spotlight
6.0
4

Recurrent Reinforcement Learning with Memoroids

NeurIPS 2024Poster
6.5
4

No Regrets: Investigating and Improving Regret Approximations for Curriculum Discovery

NeurIPS 2024Poster
7.0
3

Discovering Temporally-Aware Reinforcement Learning Algorithms

ICLR 2024Poster
5.3
4

Adam on Local Time: Addressing Nonstationarity in RL with Relative Adam Timesteps

NeurIPS 2024Poster
5.7
3

BAM! Just Like That: Simple and Efficient Parameter Upcycling for Mixture of Experts

NeurIPS 2024Poster
5.2
5

Rainbow Teaming: Open-Ended Generation of Diverse Adversarial Prompts

NeurIPS 2024Poster
合作者 (20)