Igor Mordatch

Multiagent Finetuning: Self Improvement with Diverse Reasoning Chains ICLR 2025 Generative Hierarchical Materials Search NeurIPS 2024 Improving Factuality and Reasoning in Language Models through Multiagent Debate ICML 2024 Scalable Diffusion for Materials Generation ICLR 2024 Composing Ensembles of Pre-trained Models via Iterative Consensus ICLR 2023 Grounded Decoding: Guiding Text Generation with Grounded Models for Embodied Agents NeurIPS 2023 Masked Trajectory Models for Prediction, Representation, and Control ICML 2023 Multi-Environment Pretraining Enables Transfer to Action Limited Datasets ICML 2023 PaLM-E: An Embodied Multimodal Language Model ICML 2023 RT-1: Robotics Transformer for Real-World Control at Scale RSS 2023 RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control CoRL 2023 Blocks Assemble! Learning to Assemble with Large-Scale Structured Reinforcement Learning ICML 2022 Frozen Pretrained Transformers as Universal Computation Engines AAAI 2022 Inner Monologue: Embodied Reasoning through Planning with Language Models CoRL 2022 Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents ICML 2022 Learning Iterative Reasoning through Energy Minimization ICML 2022 Multi-Game Decision Transformers NeurIPS 2022 Pre-Trained Language Models for Interactive Decision-Making NeurIPS 2022 Decision Transformer: Reinforcement Learning via Sequence Modeling NeurIPS 2021 Implicit Behavioral Cloning CoRL 2021 Improved Contrastive Divergence Training of Energy-Based Models ICML 2021 Model-Based Reinforcement Learning via Latent-Space Collocation ICML 2021 Reset-Free Lifelong Learning with Skill-Space Planning ICLR 2021 Scalable Evaluation of Multi-Agent Reinforcement Learning with Melting Pot ICML 2021 Unsupervised Learning of Compositional Energy Concepts NeurIPS 2021 A Game Theoretic Framework for Model Based Reinforcement Learning ICML 2020 Compositional Visual Generation with Energy Based Models NeurIPS 2020 Emergent Tool Use From Multi-Agent Autocurricula ICLR 2020 Gamma-Models: Generative Temporal Difference Learning for Infinite-Horizon Prediction NeurIPS 2020 One Policy to Control Them All: Shared Modular Policies for Agent-Agnostic Control ICML 2020 Implicit Generation and Modeling with Energy Based Models NeurIPS 2019 Model-Based Planning with Energy-Based Models CoRL 2019 Multi-Agent Reinforcement Learning with Multi-Step Generative Models CoRL 2019 Plan Online, Learn Offline: Efficient Learning and Exploration via Model-Based Control ICLR 2019 Continuous Adaptation via Meta-Learning in Nonstationary and Competitive Environments ICLR 2018 Emergent Complexity via Multi-Agent Competition ICLR 2018 Variance Reduction for Policy Gradient with Action-Dependent Factorized Baselines ICLR 2018 Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments NeurIPS 2017 Prediction and Control with Temporal Segment Models ICML 2017 Interactive Control of Diverse Complex Characters with Neural Networks NeurIPS 2015 Combining the benefits of function approximation and trajectory optimization RSS 2014