SOTAVerified

Imitation Learning

Imitation Learning is a framework for learning a behavior policy from demonstrations. Usually, demonstrations are presented in the form of state-action trajectories, with each pair indicating the action to take at the state being visited. In order to learn the behavior policy, the demonstrated actions are usually utilized in two ways. The first, known as Behavior Cloning (BC), treats the action as the target label for each state, and then learns a generalized mapping from states to actions in a supervised manner. Another way, known as Inverse Reinforcement Learning (IRL), views the demonstrated actions as a sequence of decisions, and aims at finding a reward/cost function under which the demonstrated decisions are optimal.

Finally, a newer methodology, Inverse Q-Learning aims at directly learning Q-functions from expert data, implicitly representing rewards, under which the optimal policy can be given as a Boltzmann distribution similar to soft Q-learning

Source: Learning to Imitate

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1151–1200 of 2122 papers

TitleStatusHype
Robots Learn Increasingly Complex Tasks with Intrinsic Motivation and Automatic Curriculum Learning—0
RoboTurk: A Crowdsourcing Platform for Robotic Skill Learning through Imitation—0
Robust Entropy-regularized Markov Decision Processes—0
On the Benefits of Inducing Local Lipschitzness for Robust Generative Adversarial Imitation Learning—0
Robust Imitation Learning for Automated Game Testing—0
Robust Imitation Learning from Corrupted Demonstrations—0
Robust Imitation of a Few Demonstrations with a Backwards Model—0
Robust Imitation of Diverse Behaviors—0
Robust Imitation via Decision-Time Planning—0
Robust Imitation via Mirror Descent Inverse Reinforcement Learning—0
Robust Instant Policy: Leveraging Student's t-Regression Model for Robust In-context Imitation Learning of Robot Manipulation—0
Robust Maximum Entropy Behavior Cloning—0
Robust Navigation for Racing Drones based on Imitation Learning and Modularization—0
Robust Offline Imitation Learning from Diverse Auxiliary Data—0
Robust Offline Imitation Learning Through State-level Trajectory Stitching—0
Robust Policy Learning via Offline Skill Diffusion—0
Robust Visual Imitation Learning with Inverse Dynamics Representations—0
RoCoDA: Counterfactual Data Augmentation for Data-Efficient Robot Learning from Demonstrations—0
Rodrigues Network for Learning Robot Actions—0
ROS-LLM: A ROS framework for embodied AI with task feedback and structured reasoning—0
RP1M: A Large-Scale Motion Dataset for Piano Playing with Bi-Manual Dexterous Robot Hands—0
RT-H: Action Hierarchies Using Language—0
RuleFuser: An Evidential Bayes Approach for Rule Injection in Imitation Learned Planners and Predictors for Robustness under Distribution Shifts—0
R+X: Retrieval and Execution from Everyday Human Videos—0
SAFARI: Safe and Active Robot Imitation Learning with Imagination—0
Efficient and Generalized end-to-end Autonomous Driving System with Latent Deep Reinforcement Learning and Demonstrations—0
Safe CoR: A Dual-Expert Approach to Integrating Imitation Learning and Safe Reinforcement Learning Using Constraint Rewards—0
Safe end-to-end imitation learning for model predictive control—0
SAFE-GIL: SAFEty Guided Imitation Learning for Robotic Systems—0
Safe Imitation Learning-based Optimal Energy Storage Systems Dispatch in Distribution Networks—0
Safe Imitation Learning on Real-Life Highway Data for Human-like Autonomous Driving—0
Safe Neural Control for Non-Affine Control Systems with Differentiable Control Barrier Functions—0
Safe Reinforcement Learning with Probabilistic Control Barrier Functions for Ramp Merging—0
Safe Trajectory Planning Using Reinforcement Learning for Self Driving—0
SafetyNet: Safe planning for real-world self-driving vehicles using machine-learned policies—0
SAIL: Faster-than-Demonstration Execution of Imitation Learning Policies—0
Saliency Prediction on Omnidirectional Images with Generative Adversarial Imitation Learning—0
Sample-efficient Adversarial Imitation Learning from Observation—0
Sample-efficient Adversarial Imitation Learning—0
Sample Efficient Imitation Learning for Continuous Control—0
Sample Efficient Imitation Learning via Reward Function Trained in Advance—0
Physics-informed Imitative Reinforcement Learning for Real-world Driving—0
Sample Efficient Interactive End-to-End Deep Learning for Self-Driving Cars with Selective Multi-Class Safe Dataset Aggregation—0
Sample Efficient Learning of Path Following and Obstacle Avoidance Behavior for Quadrotors—0
Sample Efficient Training in Multi-Agent Adversarial Games with Limited Teammate Communication—0
Scalable Bayesian Inverse Reinforcement Learning by Auto-Encoding Reward—0
Scalable Multi-Task Imitation Learning with Autonomous Improvement—0
Scaling Laws for Pre-training Agents and World Models—0
Scaling Vision-based End-to-End Driving with Multi-View Attention Learning—0
Scanpath Prediction in Panoramic Videos via Expected Code Length Minimization—0
Show:102550
← PrevPage 24 of 43Next →

No leaderboard results yet.