Sergey Levine
UC Berkeley
収録論文 315本 ・ フィジカルAI/ロボット学習
ロボット制御
※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
- 行動チャンキングがロボット制御における行動クローニングの性能を向上させる理由ロボット制御2026/8/3
行動チャンキングの性能向上の理由を実験的に検証し、既存の仮説が不十分であることを示し、遅延ポリシーや暗黙のアンサンブル効果が重要であることを明らかにした。
- Why Does Action Chunking Improve Behavioral Cloning Performance in Robotic Control?2026/8/1
- Adapting Generalist Robot Policies with Semantic Reinforcement Learning2026/6/1
- SC3-Eval: Evaluating Robot Foundation Models via Self-Consistent Video Generation2026/6/1
- Learning Process Rewards via Success Visitation Matching for Efficient RL2026/6/1
- Improving Robotic Generalist Policies via Flow Reversal Steering2026/6/1
- OGPO: Sample Efficient Full-Finetuning of Generative Control Policies2026/5/1
- RL Token: Bootstrapping Online RL with Vision-Language-Action Models2026/4/24
- ${\pi}_{0.7}$: a Steerable Generalist Robotic Foundation Model with Emergent Capabilities2026/4/1
- RL Token: Bootstrapping Online RL with Vision-Language-Action Models2026/4/1
- MEM: Multi-Scale Embodied Memory for Vision Language Action Models2026/3/1
- AsyncVLA: An Asynchronous VLA for Fast and Robust Navigation on the Edge2026/2/1
- Steerable Vision-Language-Action Policies for Embodied Reasoning and Hierarchical Control2026/2/1
- SteerVLA: Steering Vision-Language-Action Models in Long-Tail Driving Scenarios2026/2/1
- RoboReward: General-Purpose Vision-Language Reward Models for Robotics2026/1/1
- Q-learning with Adjoint Matching2026/1/1
- Decoupled Q-Chunking2025/12/1
- Training-Time Action Conditioning for Efficient Real-Time Chunking2025/12/1
- PolaRiS: Scalable Real-to-Sim Evaluations for Generalist Robot Policies2025/12/1
- Posterior Behavioral Cloning: Pretraining BC Policies for Efficient RL Finetuning2025/12/1
- Robust Finetuning of Vision-Language-Action Robot Policies via Parameter Merging2025/12/1
- Emergence of Human to Robot Transfer in Vision-Language-Action Models2025/12/1
- $π^{*}_{0.6}$: a VLA That Learns From Experience2025/11/18
- $\pi^{*}_{0.6}$: a VLA That Learns From Experience2025/11/1
- Multistep Quasimetric Learning for Scalable Goal-conditioned Reinforcement Learning2025/11/1
- Learning Affordances at Inference-Time for Vision-Language-Action Models2025/10/1
- OmniVLA: An Omni-Modal Vision-Language-Action Model for Robot Navigation2025/9/1
- CAST: Counterfactual Labels Improve Instruction Following in Vision-Language-Action Models2025/8/1
- Reinforcement Learning with Action Chunking2025/7/1
- Behavioral Exploration: Learning to Explore via In-Context Adaptation2025/7/1
- Real-Time Execution of Action Chunking Flow Policies2025/6/1
- Steering Your Diffusion Policy with Latent Space Reinforcement Learning2025/6/1
- RoboArena: Distributed Real-World Evaluation of Generalist Robot Policies2025/6/1
- Learning to Drive Anywhere with Model-Based Reannotation2025/5/1
- Training Strategies for Efficient Embodied Reasoning2025/5/1
- Knowledge Insulating Vision-Language-Action Models: Train Fast, Run Fast, Generalize Better2025/5/1
- $\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization2025/4/1
- AutoEval: Autonomous Evaluation of Generalist Robot Manipulation Policies in the Real World2025/3/1
- Hi Robot: Open-Ended Instruction Following with Hierarchical Vision-Language-Action Models2025/2/1
- Temporal Representation Alignment: Successor Features Enable Emergent Compositionality in Robot Instruction Following2025/2/1
- Reflective Planning: Vision-Language Models for Multi-Stage Long-Horizon Robotic Manipulation2025/2/1
- FAST: Efficient Action Tokenization for Vision-Language-Action Models2025/1/1
- Beyond Sight: Finetuning Generalist Robot Policies with Heterogeneous Sensors via Language Grounding2025/1/1
- RLDG: Robotic Generalist Policy Distillation via Reinforcement Learning2024/12/1
- π0: A Vision-Language-Action Flow Model for General Robot Control2024/10/1
- Precise and Dexterous Robotic Manipulation via Human-in-the-Loop Reinforcement Learning2024/10/1
- Steering Your Generalists: Improving Robotic Foundation Models via Value Guidance2024/10/1
- Traversability-Aware Legged Navigation by Learning from Real-World Visual Data2024/10/1
- GHIL-Glue: Hierarchical Control with Filtered Subgoal Images2024/10/1
- The Ingredients for Robotic Diffusion Transformers2024/10/1
- LeLaN: Learning A Language-Conditioned Navigation Policy from In-the-Wild Videos2024/10/1
- KALIE: Fine-Tuning Vision-Language Models for Open-World Manipulation without Robot Data2024/9/1
- Policy Adaptation via Language Optimization: Decomposing Tasks for Few-Shot Imitation2024/8/1
- D5RL: Diverse Datasets for Data-Driven Deep Reinforcement Learning2024/8/1
- Scaling Cross-Embodied Learning: One Policy for Manipulation, Navigation, Locomotion and Aviation2024/8/1
- Autonomous Improvement of Instruction Following Skills via Foundation Models2024/7/1
- Mobility VLA: Multimodal Instruction Navigation with Long-Context VLMs and Topological Graphs2024/7/1
- HiLMa-Res: A General Hierarchical Framework via Residual RL for Combining Quadrupedal Locomotion and Manipulation2024/7/1
- Commonsense Reasoning for Legged Robot Adaptation with Vision-Language Models2024/7/1
- Robotic Control via Embodied Chain-of-Thought Reasoning2024/7/1
- Language Guided Skill Discovery2024/6/1
- OpenVLA: An Open-Source Vision-Language-Action Model2024/6/1
- RACER: Epistemic Risk-Sensitive RL Enables Fast Driving with Fewer Crashes2024/5/1
- Octo: An Open-Source Generalist Robot Policy2024/5/1
- Evaluating Real-World Robot Manipulation Policies in Simulation2024/5/1
- Learning Visuotactile Skills with Two Multifingered Hands2024/4/1
- Yell At Your Robot: Improving On-the-Fly from Language Corrections2024/3/1
- SELFI: Autonomous Self-Improvement with Reinforcement Learning for Social Navigation2024/3/1
- MOKA: Open-World Robotic Manipulation through Mark-Based Visual Prompting2024/3/1
- DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset2024/3/1
- PIVOT: Iterative Visual Prompting Elicits Actionable Knowledge for VLMs2024/2/1
- Pushing the Limits of Cross-Embodiment Learning for Manipulation and Navigation2024/2/1
- Foundation Policies with Hilbert Representations2024/2/1
- AutoRT: Embodied Foundation Models for Large Scale Orchestration of Robotic Agents2024/1/1
- FMB: a Functional Manipulation Benchmark for Generalizable Robotic Learning2024/1/1
- Reinforcement Learning for Versatile, Dynamic, and Robust Bipedal Locomotion Control2024/1/1
- SERL: A Software Suite for Sample-Efficient Robotic Reinforcement Learning2024/1/1
- Chain of Code: Reasoning with a Language Model-Augmented Code Emulator2023/12/1
- RLIF: Interactive Imitation Learning as Reinforcement Learning2023/11/1
- Adapt On-the-Go: Behavior Modulation for Single-Life Robot Deployment2023/11/1
- METRA: Scalable Unsupervised RL with Metric-Aware Abstraction2023/10/1
- Navigation with Large Language Models: Semantic Guesswork as a Heuristic for Planning2023/10/1
- Open X-Embodiment: Robotic Learning Datasets and RT-X Models2023/10/1
- Offline Retraining for Online RL: Decoupled Policy Learning to Mitigate Exploration Bias2023/10/1
- Zero-Shot Robotic Manipulation with Pretrained Image-Editing Diffusion Models2023/10/1
- Grow Your Limits: Continuous Improvement with Real-World RL for Robotic Locomotion2023/10/1
- NoMaD: Goal Masked Diffusion Policies for Navigation and Exploration2023/10/1
- Q-Transformer: Scalable Offline Reinforcement Learning via Autoregressive Q-Functions2023/9/1
- Robotic Offline RL from Internet Videos via Value-Function Pre-Training2023/9/1
- REBOOT: Reuse Data for Bootstrapping Efficient Real-World Dexterous Manipulation2023/9/1
- Bootstrapping Adaptive Human-Machine Interfaces with Offline Reinforcement Learning2023/9/1
- BridgeData V2: A Dataset for Robot Learning at Scale2023/8/1
- Contrastive Example-Based Control2023/7/1
- HIQL: Offline Goal-Conditioned RL with Latent States as Actions2023/7/1
- Goal Representations for Instruction Following: A Semi-Supervised Language Interface to Control2023/7/1
- Multi-Stage Cable Routing through Hierarchical Imitation Learning2023/7/1
- RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control2023/7/1
- ViNT: A Foundation Model for Visual Navigation2023/6/1
- SACSoN: Scalable Autonomous Control for Social Navigation2023/6/1
- Deep RL at Scale: Sorting Waste in Office Buildings with a Fleet of Mobile Manipulators2023/5/1
- Learning and Adapting Agile Locomotion Skills by Transferring Experience2023/4/1
- Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware2023/4/1
- FastRLAP: A System for Learning High-Speed Driving via Deep RL and Autonomous Practicing2023/4/1
- Grounded Decoding: Guiding Text Generation with Grounded Models for Embodied Agents2023/3/1
- PaLM-E: An Embodied Multimodal Language Model2023/3/1
- Neural Constraint Satisfaction: Hierarchical Abstraction for Combinatorial Generalization in Object Rearrangement2023/3/1
- Robust and Versatile Bipedal Jumping Control through Reinforcement Learning2023/2/1
- Imitation Is Not Enough: Robustifying Imitation with Reinforcement Learning for Challenging Driving Scenarios2022/12/1
- RT-1: Robotics Transformer for Real-World Control at Scale2022/12/1
- Dexterous Manipulation from Images: Autonomous Real-World RL via Substep Guidance2022/12/1
- Offline Reinforcement Learning for Visual Navigation2022/12/1
- Learning Robotic Navigation from Experience: Principles, Methods, and Recent Results2022/12/1
- Robotic Skill Acquisition via Instruction Augmentation with Vision-Language Models2022/11/1
- ExAug: Robot-Conditioned Navigation Policies via Geometric Experience Augmentation2022/10/1
- Generalization with Lossy Affordances: Leveraging Broad Offline Data for Learning Visuomotor Tasks2022/10/1
- GNM: A General Navigation Model to Drive Any Robot2022/10/1
- Learning on the Job: Self-Rewarding Offline-to-Online Finetuning for Industrial Insertion of Novel Connectors from Vision2022/10/1
- Pre-Training for Robots: Offline RL Enables Learning New Tasks from a Handful of Trials2022/10/1
- GenLoco: Generalized Locomotion Controllers for Quadrupedal Robots2022/9/1
- Simplifying Model-based RL: Learning Representations, Latent-space Models, and Policies with One Objective2022/9/1
- Hierarchical Reinforcement Learning for Precise Soccer Shooting Skills using a Quadrupedal Robot2022/8/1
- A Walk in the Park: Learning to Walk in 20 Minutes With Model-Free Reinforcement Learning2022/8/1
- Don't Start From Scratch: Leveraging Prior Data to Automate Robotic Reinforcement Learning2022/7/1
- LM-Nav: Robotic Navigation with Large Pre-Trained Models of Language, Vision, and Action2022/7/1
- Inner Monologue: Embodied Reasoning through Planning with Language Models2022/7/1
- First Contact: Unsupervised Human-Machine Co-Adaptation via Mutual Information Maximization2022/5/1
- Planning to Practice: Efficient Online Fine-Tuning by Composing Goals in Latent Space2022/5/1
- INFOrmation Prioritization through EmPOWERment in Visual Model-Based RL2022/4/1
- Do As I Can, Not As I Say: Grounding Language in Robotic Affordances2022/4/1
- Control-Aware Prediction Objectives for Autonomous Driving2022/4/1
- Demonstration-Bootstrapped Autonomous Practicing via Multi-Task Reinforcement Learning2022/3/1
- ASHA: Assistive Teleoperation via Human-in-the-Loop Reinforcement Learning2022/2/1
- ViKiNG: Vision-Based Kilometer-Scale Navigation with Geographic Hints2022/2/1
- How to Leverage Unlabeled Data in Offline Reinforcement Learning2022/2/1
- BC-Z: Zero-Shot Task Generalization with Robotic Imitation Learning2022/2/1
- CoMPS: Continual Meta Policy Search2021/12/1
- Autonomous Reinforcement Learning: Formalism and Benchmarking2021/12/1
- Hybrid Imitative Planning with Geometric and Predictive Costs in Off-road Environments2021/11/1
- AW-Opt: Learning Robotic Skills with Imitation and Reinforcement at Scale2021/11/1
- Value Function Spaces: Skill-Centric State Abstractions for Long-Horizon Reasoning2021/11/1
- Offline Meta-Reinforcement Learning for Industrial Insertion2021/10/1
- Mismatched No More: Joint Model-Policy Optimization for Model-Based RL2021/10/1
- Legged Robots that Keep on Learning: Fine-Tuning Locomotion Policies in the Real World2021/10/1
- Bridge Data: Boosting Generalization of Robotic Skills with Cross-Domain Datasets2021/9/1
- Conservative Data Sharing for Multi-Task Offline Reinforcement Learning2021/9/1
- MURAL: Meta-Learning Uncertainty-Aware Rewards for Outcome-Driven Reinforcement Learning2021/7/1
- Fully Autonomous Real-World Reinforcement Learning with Applications to Mobile Manipulation2021/7/1
- Autonomous Reinforcement Learning via Subgoal Curricula2021/7/1
- Offline Meta-Reinforcement Learning with Online Self-Supervision2021/7/1
- Model-Based Reinforcement Learning via Latent-Space Collocation2021/6/1
- Hierarchically Integrated Models: Learning to Navigate from Heterogeneous Robots2021/6/1
- What Can I Do Here? Learning New Skills by Imagining Visual Affordances2021/6/1
- Actionable Models: Unsupervised Offline Reinforcement Learning of Robotic Skills2021/4/1
- MT-Opt: Continuous Multi-Task Robotic Reinforcement Learning at Scale2021/4/1
- DisCo RL: Distribution-Conditioned Reinforcement Learning for General-Purpose Policies2021/4/1
- Reset-Free Reinforcement Learning via Multi-Task Learning: Learning Dexterous Manipulation Behaviors without Human Intervention2021/4/1
- Contingencies from Observations: Tractable Contingency Planning with Learned Behavior Models2021/4/1
- Rapid Exploration for Open-World Navigation with Latent Goal Models2021/4/1
- Maximum Entropy RL (Provably) Solves Some Robust RL Problems2021/3/1
- Replacing Rewards with Examples: Example-Based Policy Search via Recursive Classification2021/3/1
- Reinforcement Learning for Robust Parameterized Locomotion Control of Bipedal Robots2021/3/1
- COMBO: Conservative Offline Model-Based Policy Optimization2021/2/1
- How to Train Your Robot with Deep Reinforcement Learning; Lessons We've Learned2021/2/1
- SimGAN: Hybrid Simulator Identification for Domain Adaptation via Adversarial Reinforcement Learning2021/1/1
- Model-Based Visual Planning with Self-Supervised Functional Distances2020/12/1
- ViNG: Learning Open-World Navigation with Visual Goals2020/12/1
- Reinforcement Learning with Videos: Combining Offline Observations with Interaction2020/11/1
- Parrot: Data-Driven Behavioral Priors for Reinforcement Learning2020/11/1
- Rearrangement: A Challenge for Embodied AI2020/11/1
- MELD: Meta-Reinforcement Learning from Images via Latent State Models2020/10/1
- COG: Connecting New Skills to Past Experience with Offline Reinforcement Learning2020/10/1
- Conservative Safety Critics for Exploration2020/10/1
- LaND: Learning to Navigate from Disengagements2020/10/1
- Assisted Perception: Optimizing Observations to Communicate State2020/8/1
- AWAC: Accelerating Online Reinforcement Learning with Offline Datasets2020/6/1
- RL-CycleGAN: Reinforcement Learning Aware Simulation-To-Real2020/6/1
- Can Autonomous Vehicles Identify, Recover From, and Adapt to Distribution Shifts?2020/6/1
- Long-Horizon Visual Planning with Goal-Conditioned Hierarchical Predictors2020/6/1
- Off-Dynamics Reinforcement Learning: Training for Transfer with Domain Classifiers2020/6/1
- Learning Agile Robotic Locomotion Skills by Imitating Animals2020/4/1
- Model-Based Meta-Reinforcement Learning for Flight with Suspended Payloads2020/4/1
- Meta-Reinforcement Learning for Robotic Industrial Insertion Tasks2020/4/1
- Emergent Real-World Robotic Skills via Unsupervised Off-Policy Reinforcement Learning2020/4/1
- The Ingredients of Real-World Robotic Reinforcement Learning2020/4/1
- Never Stop Learning: The Effectiveness of Fine-Tuning in Robotic Reinforcement Learning2020/4/1
- Thinking While Moving: Deep Reinforcement Learning with Concurrent Control2020/4/1
- OmniTact: A Multi-Directional High Resolution Touch Sensor2020/3/1
- Inverting the Pose Forecasting Pipeline with SPF2: Sequential Pointcloud Forecasting for Sequential Pose Forecasting2020/3/1
- Scalable Multi-Task Imitation Learning with Autonomous Improvement2020/3/1
- Learning to Walk in the Real World with Minimal Human Effort2020/2/1
- Rewriting History with Inverse RL: Hindsight Inference for Policy Improvement2020/2/1
- BADGR: An Autonomous Self-Supervised Learning-Based Navigation System2020/2/1
- Gradient Surgery for Multi-Task Learning2020/1/1
- Morphology-Agnostic Visual Robotic Control2019/12/1
- AVID: Learning Multi-Stage Tasks via Pixel-Level Translation of Human Videos2019/12/1
- Learning Predictive Models From Observation and Interaction2019/12/1
- Planning with Goal-Conditioned Policies2019/11/1
- Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning2019/10/1
- RoboNet: Large-Scale Multi-Robot Learning2019/10/1
- Contextual Imagined Goals for Self-Supervised Robotic Learning2019/10/1
- Scaled Autonomy: Enabling Human Operators to Control Robot Fleets2019/10/1
- Plan Arithmetic: Compositional Plan Vectors for Multi-Task Control2019/10/1
- Relay Policy Learning: Solving Long-Horizon Tasks via Imitation and Reinforcement Learning2019/10/1
- Deep Dynamics Models for Learning Dexterous Manipulation2019/9/1
- ROBEL: Robotics Benchmarks for Learning with Low-Cost Robots2019/9/1
- Dynamics-Aware Unsupervised Discovery of Skills2019/7/1
- Dynamical Distance Learning for Semi-Supervised and Unsupervised Skill Discovery2019/7/1
- Off-Policy Evaluation via Off-Policy Classification2019/6/1
- Search on the Replay Buffer: Bridging Planning and Reinforcement Learning2019/6/1
- Deep Reinforcement Learning for Industrial Insertion Tasks with Visual Inputs and Natural Rewards2019/6/1
- Efficient Exploration via State Marginal Matching2019/6/1
- REPLAB: A Reproducible Low-Cost Arm Benchmark Platform for Robotic Learning2019/5/1
- Data-efficient Learning of Morphology and Controller for a Microrobot2019/5/1
- PRECOG: PREdiction Conditioned On Goals in Visual Multi-Agent Settings2019/5/1
- Safety Augmented Value Estimation from Demonstrations (SAVED): Safe Deep Model-Based RL for Sparse Cost Robotic Tasks2019/5/1
- End-to-End Robotic Reinforcement Learning without Reward Engineering2019/4/1
- Improvisation through Physical Understanding: Using Novel Objects as Tools with Visual Foresight2019/4/1
- Guided Meta-Policy Search2019/4/1
- Learning Latent Plans from Play2019/3/1
- Skew-Fit: State-Covering Self-Supervised Reinforcement Learning2019/3/1
- Manipulation by Feel: Touch-Based Control with Deep Predictive Models2019/3/1
- Learning to Identify Object Instances by Touch: Tactile Recognition via Multimodal Matching2019/3/1
- Generalization through Simulation: Integrating Simulated and Real Data into Deep Reinforcement Learning for Vision-Based Autonomous Flight2019/2/1
- Artificial Intelligence for Prosthetics - challenge solutions2019/2/1
- Low Level Control of a Quadrotor with Deep Model-Based Reinforcement Learning2019/1/1
- Deep Online Learning via Meta-Learning: Continual Adaptation for Model-Based RL2018/12/1
- Residual Reinforcement Learning for Robot Control2018/12/1
- Learning to Walk via Deep Reinforcement Learning2018/12/1
- Visual Foresight: Model-Based Deep Reinforcement Learning for Vision-Based Robotic Control2018/12/1
- Visual Memory for Robust Path Following2018/12/1
- Soft Actor-Critic Algorithms and Applications2018/12/1
- Sim-to-Real via Sim-to-Sim: Data-efficient Robotic Grasping via Randomized-to-Canonical Adaptation Networks2018/12/1
- Reasoning About Physical Interactions with Object-Oriented Prediction and Planning2018/12/1
- Grasp2Vec: Learning Object Representations from Self-Supervised Grasping2018/11/1
- Hierarchical Policy Design for Sample-Efficient Learning of Robot Table Tennis Through Self-Play2018/11/1
- Deep Imitative Models for Flexible Inference, Planning, and Control2018/10/1
- Composable Action-Conditioned Predictors: Flexible Off-Policy Learning for Robot Navigation2018/10/1
- Robustness via Retrying: Closed-Loop Robotic Manipulation with Self-Supervised Learning2018/10/1
- One-Shot Hierarchical Imitation Learning of Compound Visuomotor Tasks2018/10/1
- Dexterous Manipulation with Deep Reinforcement Learning: Efficient, General, and Low-Cost2018/10/1
- Few-Shot Goal Inference for Visuomotor Learning and Planning2018/10/1
- Time Reversal as Self-Supervision2018/10/1
- SOLAR: Deep Structured Representations for Model-Based Reinforcement Learning2018/8/1
- Visual Reinforcement Learning with Imagined Goals2018/7/1
- Learning Instance Segmentation by Interaction2018/6/1
- QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation2018/6/1
- Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models2018/5/1
- Reinforcement Learning and Control as Probabilistic Inference: Tutorial and Review2018/5/1
- More Than a Feeling: Learning to Grasp and Regrasp using Vision and Touch2018/5/1
- Universal Planning Networks2018/4/1
- Stochastic Adversarial Video Prediction2018/4/1
- Learning Flexible and Reusable Locomotion Primitives for a Microrobot2018/3/1
- Learning to Adapt in Dynamic, Real-World Environments Through Meta-Reinforcement Learning2018/3/1
- Composable Deep Reinforcement Learning for Robotic Manipulation2018/3/1
- Deep Reinforcement Learning for Vision-Based Robotic Grasping: A Simulated Comparative Evaluation of Off-Policy Methods2018/2/1
- Diversity is All You Need: Learning Skills without a Reward Function2018/2/1
- Shared Autonomy via Deep Reinforcement Learning2018/2/1
- One-Shot Imitation from Observing Humans via Domain-Adaptive Meta-Learning2018/2/1
- Unifying Map and Landmark Based Representations for Visual Navigation2017/12/1
- Sim2Real View Invariant Visual Servoing by Recurrent Control2017/12/1
- Divide-and-Conquer Reinforcement Learning2017/11/1
- Learning Image-Conditioned Dynamics Models for Control of Under-actuated Legged Millirobots2017/11/1
- Leave no Trace: Learning to Reset for Safe and Autonomous Reinforcement Learning2017/11/1
- The Feeling of Success: Does Touch Sensing Help Predict Grasp Outcomes?2017/10/1
- Stochastic Variational Video Prediction2017/10/1
- Self-Supervised Visual Planning with Temporal Skip Connections2017/10/1
- Using Simulation and Domain Adaptation to Improve Efficiency of Deep Robotic Grasping2017/9/1
- Learning Robotic Manipulation of Granular Media2017/9/1
- One-Shot Visual Imitation Learning via Meta-Learning2017/9/1
- Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrations2017/9/1
- Self-supervised Deep Reinforcement Learning with Generalized Computation Graphs for Robot Navigation2017/9/1
- MBMF: Model-Based Priors for Model-Free Reinforcement Learning2017/9/1
- GPLAC: Generalizing Vision-Based Robotic Skills using Weakly Labeled Images2017/8/1
- Neural Network Dynamics for Model-Based Deep Reinforcement Learning with Model-Free Fine-Tuning2017/8/1
- Deep Object-Centric Representations for Generalizable Robot Learning2017/8/1
- Vision-Based Multi-Task Manipulation for Inexpensive Robots Using End-To-End Learning from Demonstration2017/7/1
- End-to-End Learning of Semantic Grasping2017/7/1
- Imitation from Observation: Learning to Imitate Behaviors from Raw Video via Context Translation2017/7/1
- Interpolated Policy Gradient: Merging On-Policy and Off-Policy Gradient Estimation for Deep Reinforcement Learning2017/6/1
- Time-Contrastive Networks: Self-Supervised Learning from Video2017/4/1
- Combining Model-Based and Model-Free Updates for Trajectory-Centric Reinforcement Learning2017/3/1
- Learning Visual Servoing with Deep Features and Fitted Q-Iteration2017/3/1
- Learning Invariant Feature Spaces to Transfer Skills with Reinforcement Learning2017/3/1
- Combining Self-Supervised Learning and Imitation for Vision-Based Rope Manipulation2017/3/1
- Cognitive Mapping and Planning for Visual Navigation2017/2/1
- Uncertainty-Aware Reinforcement Learning for Collision Avoidance2017/2/1
- Generalizing Skills with Semi-Supervised Reinforcement Learning2016/12/1
- Unsupervised Perceptual Rewards for Imitation Learning2016/12/1
- Learning Dexterous Manipulation Policies from Experience and Imitation2016/11/1
- CAD2RL: Real Single-Image Flight without a Single Real Image2016/11/1
- Path Integral Guided Policy Search2016/10/1
- Deep Visual Foresight for Planning Robot Motion2016/10/1
- Collective Robot Reinforcement Learning with Distributed Asynchronous Guided Policy Search2016/10/1
- EPOpt: Learning Robust Neural Network Policies Using Model Ensembles2016/10/1
- Deep Reinforcement Learning for Robotic Manipulation with Asynchronous Off-Policy Updates2016/10/1
- Reset-Free Guided Policy Search: Efficient Deep Reinforcement Learning with Stochastic Initial States2016/10/1
- Learning from the Hindsight Plan -- Episodic MPC Improvement2016/9/1
- Deep Reinforcement Learning for Tensegrity Robot Locomotion2016/9/1
- Learning Modular Neural Network Policies for Multi-Task and Multi-Robot Transfer2016/9/1
- Guided Policy Search as Approximate Mirror Descent2016/7/1
- Learning to Poke by Poking: Experiential Learning of Intuitive Physics2016/6/1
- Unsupervised Learning for Physical Interaction through Video Prediction2016/5/1
- Continuous Deep Q-Learning with Model-based Acceleration2016/3/1
- Learning Hand-Eye Coordination for Robotic Grasping with Deep Learning and Large-Scale Data Collection2016/3/1
- Guided Cost Learning: Deep Inverse Optimal Control via Policy Optimization2016/3/1
- Learning Dexterous Manipulation for a Soft Robotic Hand from Human Demonstration2016/3/1
- One-Shot Learning of Manipulation Skills with Online Dynamics Adaptation and Neural Network Priors2015/9/1
- Model-based Reinforcement Learning with Parametrized Physical Models and Optimism-Driven Exploration2015/9/1
- Deep Spatial Autoencoders for Visuomotor Learning2015/9/1
- Learning Deep Control Policies for Autonomous Aerial Vehicles with MPC-Guided Policy Search2015/9/1
- Learning Deep Neural Network Policies with Continuous Memory States2015/7/1
- High-Dimensional Continuous Control Using Generalized Advantage Estimation2015/6/1
- End-to-End Training of Deep Visuomotor Policies2015/4/1
- Learning Contact-Rich Manipulation Skills with Guided Policy Search2015/1/1
- Exploring Deep and Recurrent Architectures for Optimal Control2013/11/1