Nathan Grinsztajn
6 papers · 2021–2024 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+3 more ↓ Show less ↑
π Cross-Pollinator (15) π Conference Polyglot (4) πΊοΈ Taxonomy Completionist (15) π§ Keyword Pioneer π Renaissance Researcher (5)
π
Interdisciplinary Bridge
π₯
Mega-Team
(24)
β
The Questioner
Conferences
NIPS (3)
EMNLP (1)
ICLR (1)
ICML (1)
Top co-authors
Keywords
reinforcement learning
(3)
combinatorial optimization
(2)
travelling salesman problem
(2)
vehicle routing problem
(2)
self-supervised learning
(1)
preference optimization
(1)
model alignment
(1)
off-policy learning
(1)
reversibility-aware exploration
(1)
policy adaptation
(1)
language model finetuning
(1)
vehicle routing
(1)
irreversible action
(1)
sequence-level optimization
(1)
population-based training
(1)
population training
(1)
temporal ordering
(1)
large language model
(1)
job shop scheduling
(1)
traveling salesman
(1)
Papers
Contrastive Policy Gradient: Aligning LLMs on sequence-level scores in a supervised-friendly fashion
EMNLP 2024
Jumanji: a Diverse Suite of Scalable Reinforcement Learning Environments in JAX
ICLR 2024
Should we be going MAD? A Look at Multi-Agent Debate Strategies for LLMs
ICML 2024
Combinatorial Optimization with Policy Adaptation using Latent Space Search
NIPS 2023
Winner Takes It All: Training Performant RL Populations for Combinatorial Optimization
NIPS 2023
There Is No Turning Back: A Self-Supervised Approach for Reversibility-Aware Reinforcement Learning
NIPS 2021