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 451–500 of 2122 papers

TitleStatusHype
ELA: Exploited Level Augmentation for Offline Learning in Zero-Sum Games—0
DexGraspVLA: A Vision-Language-Action Framework Towards General Dexterous Grasping—0
DexMimicGen: Automated Data Generation for Bimanual Dexterous Manipulation via Imitation Learning—0
Deep Bayesian Reward Learning from Preferences—0
Bayesian Multi-type Mean Field Multi-agent Imitation Learning—0
Dexterous Imitation Made Easy: A Learning-Based Framework for Efficient Dexterous Manipulation—0
Dexterous Manipulation through Imitation Learning: A Survey—0
A Linearly Constrained Nonparametric Framework for Imitation Learning—0
Decoupling Skill Learning from Robotic Control for Generalizable Object Manipulation—0
DIAL: Distribution-Informed Adaptive Learning of Multi-Task Constraints for Safety-Critical Systems—0
Analyzing an Imitation Learning Network for Fundus Image Registration Using a Divide-and-Conquer Approach—0
Bayesian Learning for Dynamic Inference—0
Efficient Imitation Learning with Conservative World Models—0
Bayesian Imitation Learning for End-to-End Mobile Manipulation—0
Differentiable Constrained Imitation Learning for Robot Motion Planning and Control—0
An Analysis of Logit Learning with the r-Lambert Function—0
Differentiable Robust LQR Layers—0
DiffStitch: Boosting Offline Reinforcement Learning with Diffusion-based Trajectory Stitching—0
Decomposing the Generalization Gap in Imitation Learning for Visual Robotic Manipulation—0
AdaManip: Adaptive Articulated Object Manipulation Environments and Policy Learning—0
Batch Recurrent Q-Learning for Backchannel Generation Towards Engaging Agents—0
Synthesizing Decentralized Controllers with Graph Neural Networks and Imitation Learning—0
Diffusion Imitation from Observation—0
Diffusion Meets DAgger: Supercharging Eye-in-hand Imitation Learning—0
Diffusion Model-Augmented Behavioral Cloning—0
Diffusion Models for Robotic Manipulation: A Survey—0
Diffusion-Reward Adversarial Imitation Learning—0
DIGIC: Domain Generalizable Imitation Learning by Causal Discovery—0
Align Your Intents: Offline Imitation Learning via Optimal Transport—0
DINOBot: Robot Manipulation via Retrieval and Alignment with Vision Foundation Models—0
DINO Pre-training for Vision-based End-to-end Autonomous Driving—0
Directed-Info GAIL: Learning Hierarchical Policies from Unsegmented Demonstrations using Directed Information—0
DIRECT: Learning from Sparse and Shifting Rewards using Discriminative Reward Co-Training—0
Efficient Fusion and Task Guided Embedding for End-to-end Autonomous Driving—0
Discovering Generalizable Spatial Goal Representations via Graph-based Active Reward Learning—0
Discovering hierarchies using Imitation Learning from hierarchy aware policies—0
Efficient Imitation under Misspecification—0
BOSS: Benchmark for Observation Space Shift in Long-Horizon Task—0
Discriminator-Guided Model-Based Offline Imitation Learning—0
DEALIO: Data-Efficient Adversarial Learning for Imitation from Observation—0
DDIL: Diversity Enhancing Diffusion Distillation With Imitation Learning—0
ADAIL: Adaptive Adversarial Imitation Learning—0
D-CODA: Diffusion for Coordinated Dual-Arm Data Augmentation—0
Dissipative Imitation Learning for Robust Dynamic Output Feedback—0
Data Quality in Imitation Learning—0
Accelerating Self-Imitation Learning from Demonstrations via Policy Constraints and Q-Ensemble—0
Distilling Privileged Information for Dubins Traveling Salesman Problems with Neighborhoods—0
Distilling Realizable Students from Unrealizable Teachers—0
Distributional Decision Transformer for Hindsight Information Matching—0
DataMIL: Selecting Data for Robot Imitation Learning with Datamodels—0
Show:102550
← PrevPage 10 of 43Next →

No leaderboard results yet.