Nicolas Heess
収録論文 60本 ・ フィジカルAI/ロボット学習
※arXiv著者名で収集。同姓同名の別人の論文が含まれる場合があります。
論文
- Gemini Robotics 1.5: Pushing the Frontier of Generalist Robots with Advanced Embodied Reasoning, Thinking, and Motion Transfer2025/10/1
- Exploiting Policy Idling for Dexterous Manipulation2025/8/1
- ExoStart: Efficient learning for dexterous manipulation with sensorized exoskeleton demonstrations2025/6/1
- Gemini Robotics: Bringing AI into the Physical World2025/3/1
- Proc4Gem: Foundation models for physical agency through procedural generation2025/3/1
- DemoStart: Demonstration-led auto-curriculum applied to sim-to-real with multi-fingered robots2024/9/1
- Deep Dive into Model-free Reinforcement Learning for Biological and Robotic Systems: Theory and Practice2024/5/1
- Learning Robot Soccer from Egocentric Vision with Deep Reinforcement Learning2024/5/1
- PIVOT: Iterative Visual Prompting Elicits Actionable Knowledge for VLMs2024/2/1
- Learning to Learn Faster from Human Feedback with Language Model Predictive Control2024/2/1
- Offline Actor-Critic Reinforcement Learning Scales to Large Models2024/2/1
- Mastering Stacking of Diverse Shapes with Large-Scale Iterative Reinforcement Learning on Real Robots2023/12/1
- Foundations for Transfer in Reinforcement Learning: A Taxonomy of Knowledge Modalities2023/12/1
- Replay across Experiments: A Natural Extension of Off-Policy RL2023/11/1
- Open X-Embodiment: Robotic Learning Datasets and RT-X Models2023/10/1
- Towards A Unified Agent with Foundation Models2023/7/1
- RoboCat: A Self-Improving Generalist Agent for Robotic Manipulation2023/6/1
- Language to Rewards for Robotic Skill Synthesis2023/6/1
- Barkour: Benchmarking Animal-level Agility with Quadruped Robots2023/5/1
- A Generalist Dynamics Model for Control2023/5/1
- Learning Agile Soccer Skills for a Bipedal Robot with Deep Reinforcement Learning2023/4/1
- Lossless Adaptation of Pretrained Vision Models For Robotic Manipulation2023/4/1
- Leveraging Jumpy Models for Planning and Fast Learning in Robotic Domains2023/2/1
- SkillS: Adaptive Skill Sequencing for Efficient Temporally-Extended Exploration2022/11/1
- NeRF2Real: Sim2real Transfer of Vision-guided Bipedal Motion Skills using Neural Radiance Fields2022/10/1
- MO2: Model-Based Offline Options2022/9/1
- A Generalist Agent2022/5/1
- Forgetting and Imbalance in Robot Lifelong Learning with Off-policy Data2022/4/1
- Imitate and Repurpose: Learning Reusable Robot Movement Skills From Human and Animal Behaviors2022/3/1
- Learning Transferable Motor Skills with Hierarchical Latent Mixture Policies2021/12/1
- Learning Coordinated Terrain-Adaptive Locomotion by Imitating a Centroidal Dynamics Planner2021/11/1
- Offline Meta-Reinforcement Learning for Industrial Insertion2021/10/1
- Evaluating model-based planning and planner amortization for continuous control2021/10/1
- Learning Dynamics Models for Model Predictive Agents2021/9/1
- Is Curiosity All You Need? On the Utility of Emergent Behaviours from Curious Exploration2021/9/1
- On Multi-objective Policy Optimization as a Tool for Reinforcement Learning: Case Studies in Offline RL and Finetuning2021/6/1
- From Motor Control to Team Play in Simulated Humanoid Football2021/5/1
- Learning Dexterous Manipulation from Suboptimal Experts2020/10/1
- Beyond Tabula-Rasa: a Modular Reinforcement Learning Approach for Physically Embedded 3D Sokoban2020/10/1
- Towards General and Autonomous Learning of Core Skills: A Case Study in Locomotion2020/8/1
- Data-efficient Hindsight Off-policy Option Learning2020/7/1
- dm_control: Software and Tasks for Continuous Control2020/6/1
- Simple Sensor Intentions for Exploration2020/5/1
- A Distributional View on Multi-Objective Policy Optimization2020/5/1
- Keep Doing What Worked: Behavioral Modelling Priors for Offline Reinforcement Learning2020/2/1
- Continuous-Discrete Reinforcement Learning for Hybrid Control in Robotics2020/1/1
- Catch & Carry: Reusable Neural Controllers for Vision-Guided Whole-Body Tasks2019/11/1
- Imagined Value Gradients: Model-Based Policy Optimization with Transferable Latent Dynamics Models2019/10/1
- Compositional Transfer in Hierarchical Reinforcement Learning2019/6/1
- Value constrained model-free continuous control2019/2/1
- Self-supervised Learning of Image Embedding for Continuous Control2019/1/1
- Neural probabilistic motor primitives for humanoid control2018/11/1
- Hierarchical visuomotor control of humanoids2018/11/1
- Maximum a Posteriori Policy Optimisation2018/6/1
- Reinforcement and Imitation Learning for Diverse Visuomotor Skills2018/2/1
- Learning by Playing - Solving Sparse Reward Tasks from Scratch2018/2/1
- Learning human behaviors from motion capture by adversarial imitation2017/7/1
- Data-efficient Deep Reinforcement Learning for Dexterous Manipulation2017/4/1
- Learning and Transfer of Modulated Locomotor Controllers2016/10/1
- Sim-to-Real Robot Learning from Pixels with Progressive Nets2016/10/1