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 101–150 of 2122 papers

TitleStatusHype
Coherent Soft Imitation LearningCode1
Learning to combine primitive skills: A step towards versatile robotic manipulationCode1
All You Need Is Supervised Learning: From Imitation Learning to Meta-RL With Upside Down RLCode1
Generalization Guarantees for Imitation LearningCode1
Confidence-Aware Imitation Learning from Demonstrations with Varying OptimalityCode1
Generative Adversarial Imitation LearningCode1
Goal-Auxiliary Actor-Critic for 6D Robotic Grasping with Point CloudsCode1
Learning Constrained Adaptive Differentiable Predictive Control Policies With GuaranteesCode1
HAD-Gen: Human-like and Diverse Driving Behavior Modeling for Controllable Scenario GenerationCode1
Go-Explore: a New Approach for Hard-Exploration ProblemsCode1
Exact Combinatorial Optimization with Graph Convolutional Neural NetworksCode1
Exciting Action: Investigating Efficient Exploration for Learning Musculoskeletal Humanoid LocomotionCode1
CRIL: Continual Robot Imitation Learning via Generative and Prediction ModelCode1
Critic Guided Segmentation of Rewarding Objects in First-Person ViewsCode1
Crossway Diffusion: Improving Diffusion-based Visuomotor Policy via Self-supervised LearningCode1
Curriculum Offline Imitation LearningCode1
An Empirical Investigation of Representation Learning for ImitationCode1
Curricular Subgoals for Inverse Reinforcement LearningCode1
How To Guide Your Learner: Imitation Learning with Active Adaptive Expert InvolvementCode1
DART: Noise Injection for Robust Imitation LearningCode1
DeeCap: Dynamic Early Exiting for Efficient Image CaptioningCode1
An Imitation Game for Learning Semantic Parsers from User InteractionCode1
A Competition Winning Deep Reinforcement Learning Agent in microRTSCode1
iCurb: Imitation Learning-based Detection of Road Curbs using Aerial Images for Autonomous DrivingCode1
A Divergence Minimization Perspective on Imitation Learning MethodsCode1
Causal Imitation Learning under Temporally Correlated NoiseCode1
EvIL: Evolution Strategies for Generalisable Imitation LearningCode1
Explorative Imitation Learning: A Path Signature Approach for Continuous EnvironmentsCode1
CALVIN: A Benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation TasksCode1
A GAN-Like Approach for Physics-Based Imitation Learning and Interactive Character ControlCode1
Causal Imitative Model for Autonomous DrivingCode1
CAFE-AD: Cross-Scenario Adaptive Feature Enhancement for Trajectory Planning in Autonomous DrivingCode1
Can We Detect Failures Without Failure Data? Uncertainty-Aware Runtime Failure Detection for Imitation Learning PoliciesCode1
Everyone Deserves A Reward: Learning Customized Human PreferencesCode1
f-GAIL: Learning f-Divergence for Generative Adversarial Imitation LearningCode1
Bridging the Gap Between Learning in Discrete and Continuous Environments for Vision-and-Language NavigationCode1
Energy-Based Imitation LearningCode1
Active Imitation Learning with Noisy GuidanceCode1
Adversarial Soft Advantage Fitting: Imitation Learning without Policy OptimizationCode1
End-to-End Urban Driving by Imitating a Reinforcement Learning CoachCode1
Adversarial Option-Aware Hierarchical Imitation LearningCode1
Emergent Communication at ScaleCode1
End-to-End Egospheric Spatial MemoryCode1
Bootstrapped Model Predictive ControlCode1
When should we prefer Decision Transformers for Offline Reinforcement Learning?Code1
CACTI: A Framework for Scalable Multi-Task Multi-Scene Visual Imitation LearningCode1
End-to-End Imitation Learning with Safety Guarantees using Control Barrier FunctionsCode1
Estimating Q(s,s') with Deep Deterministic Dynamics GradientsCode1
FILM: Following Instructions in Language with Modular MethodsCode1
EDITOR: an Edit-Based Transformer with Repositioning for Neural Machine Translation with Soft Lexical ConstraintsCode1
Show:102550
← PrevPage 3 of 43Next →

No leaderboard results yet.