Imitation Learning
Overview
Imitation learning teaches an agent to act by using examples of how a person or expert system behaves, often when specifying a reward is difficult. Behavior cloning directly maps observations to actions, while DAgger adds expert corrections on states the learner encounters, and inverse or adversarial imitation learning infers what behavior to match. Current methods also use diffusion policies, retrieval, world models, and visual, language, or tactile data for tasks such as robot manipulation, autonomous driving, and multi-agent coordination, with benchmarks including LIBERO, RoboMimic, and CARLA. A central challenge is that small errors can lead agents into states missing from demonstrations; improving recovery and safety while learning efficiently from limited, noisy, or conflicting examples remains an open tension.
Latest papers
287 papers37 papers in the last four weeks, up 6% on the four weeks before. 0.3% of all new papers.
Imitation Learning for Connection-Tableau Construction
One-Shot Learning from Demonstration of Contact-Rich Robotic Manipulation by Identifying Physical Interactions
Dynamical System-Based Imitation Learning and Neuroadaptive Control for Trajectory Recovery in Autonomous Ships
The Imitator Game: Benchmarking Robot Imitative Ability Beyond Action Prediction
On the Capability Separation Between World-Model Policy Learning and Imitated World-Action Models
Vision Guided Target Conditioned Control for Autonomous Excavation
Neural-Primitive: An Efficient End-to-end Local Planner with Primitive-based Imitation Learning for Autonomous Flight
FigmaTrace: Capturing Creative Nuances in Human Figma Design Workflows
UniReflex: Plug-and-Play Force Control for Pretrained Generative Policies via Fast-Slow Reflex
RAPAC-DP: Response-Aligned Pending-Action Compensation for Diffusion Policies under Delayed Execution
Max-Q Selective Imitation for Human-in-the-Loop Online Robot Learning
PILOT: Privileged Imitation Learning for End-to-End Motion Planning of Autonomous UAVs under Partial Observability
The Next Screenshot Knows: Gated Hindsight Distillation for Mobile GUI Agents
Learning Clinical-Trial Strategy: Offline Policy Training for Decision Agents
Tired Actor: Fatigue-Informed Character Control
A Hierarchical Approach to Imitation Learning for Manipulation Tasks Requiring Time Varying Forces
DynamicManip: Enabling Dynamic Manipulation from a Single Static Demonstration
When Does On-Policy Interaction Help? Representational Tradeoffs in Value-Based Imitation Learning
Mirror Learning
LM-GRASP: Instance-Specific Language Models for Combinatorial Construction via Online Imitation Learning
It's Not Just More Demos: Counterfactual Action Sensitivity Coverage for Data-Efficient Robust Robot Imitation
nuisances', with even minor task-preserving variations such as lighting, distractions or changes in colour result in heavy degradation of the trained policy's performance. While increasing data diversity can improve robustness, it is unclear which additional demonstrations are informative for a particular trained policy. We propose Counterfactual Nuisance Behaviour Cloning (CFNBC), an offline data-selection framework for targeted robustness repair. Starting from a nominal policy trained on clean' demonstrations, CFNBC generates paired clean and nuisance observations that preserve the expert action, then measures action drift: the change in the policy's predicted action under a nuisance that should not alter the desired behaviour. This provides a policy-specific sensitivity signal for selecting a compact, response-diverse repair set from a larger candidate pool, without requiring rollout success labels or online policy execution. We show in MuJoCo bimanual cube transfer and SimplerEnv cube stacking that action drift correlates with nuisance-induced failure, and that response-guided repair with only -- selected candidates substantially outperforms matched-budget random selection while approaching the performance of much larger random repair budgets. These results support a data-centric view of robustness repair: the most useful data are not necessarily the most numerous, visually diverse, or obviously difficult, but the examples that cover fragile response modes of the current policy.