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
Frame Mining: a Free Lunch for Learning Robotic Manipulation from 3D Point CloudsCode1
Generalization Guarantees for Imitation LearningCode1
All You Need Is Supervised Learning: From Imitation Learning to Meta-RL With Upside Down RLCode1
Confidence-Aware Imitation Learning from Demonstrations with Varying OptimalityCode1
Generalized Decision Transformer for Offline Hindsight Information MatchingCode1
Learning Constrained Adaptive Differentiable Predictive Control Policies With GuaranteesCode1
CRIL: Continual Robot Imitation Learning via Generative and Prediction ModelCode1
Global Tensor Motion PlanningCode1
Guiding Data Collection via Factored Scaling CurvesCode1
Counter-Strike Deathmatch with Large-Scale Behavioural CloningCode1
Causal Imitation Learning under Temporally Correlated NoiseCode1
An Adversarial Imitation Click Model for Information RetrievalCode1
Curricular Subgoals for Inverse Reinforcement LearningCode1
Crossway Diffusion: Improving Diffusion-based Visuomotor Policy via Self-supervised LearningCode1
Curriculum Offline Imitation LearningCode1
Causal Imitative Model for Autonomous DrivingCode1
An Empirical Investigation of Representation Learning for ImitationCode1
DART: Noise Injection for Robust Imitation LearningCode1
Explorative Imitation Learning: A Path Signature Approach for Continuous EnvironmentsCode1
Deep Imitation Learning for Bimanual Robotic ManipulationCode1
How To Guide Your Learner: Imitation Learning with Active Adaptive Expert InvolvementCode1
An Imitation Game for Learning Semantic Parsers from User InteractionCode1
A Competition Winning Deep Reinforcement Learning Agent in microRTSCode1
Hybrid Inverse Reinforcement LearningCode1
A Divergence Minimization Perspective on Imitation Learning MethodsCode1
IGDrivSim: A Benchmark for the Imitation Gap in Autonomous DrivingCode1
Exciting Action: Investigating Efficient Exploration for Learning Musculoskeletal Humanoid LocomotionCode1
f-GAIL: Learning f-Divergence for Generative Adversarial Imitation LearningCode1
Everyone Deserves A Reward: Learning Customized Human PreferencesCode1
A GAN-Like Approach for Physics-Based Imitation Learning and Interactive Character ControlCode1
EvIL: Evolution Strategies for Generalisable Imitation LearningCode1
Can We Detect Failures Without Failure Data? Uncertainty-Aware Runtime Failure Detection for Imitation Learning PoliciesCode1
CDT: Cascading Decision Trees for Explainable Reinforcement LearningCode1
Exact Combinatorial Optimization with Graph Convolutional Neural NetworksCode1
FILM: Following Instructions in Language with Modular MethodsCode1
CACTI: A Framework for Scalable Multi-Task Multi-Scene Visual 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
CAFE-AD: Cross-Scenario Adaptive Feature Enhancement for Trajectory Planning in Autonomous DrivingCode1
Adversarial Option-Aware Hierarchical Imitation LearningCode1
End-to-End Imitation Learning with Safety Guarantees using Control Barrier FunctionsCode1
CALVIN: A Benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation TasksCode1
When should we prefer Decision Transformers for Offline Reinforcement Learning?Code1
Chain-of-Thought Predictive ControlCode1
End-to-End Urban Driving by Imitating a Reinforcement Learning CoachCode1
Estimating Q(s,s') with Deep Deterministic Dynamics GradientsCode1
Embodied Multi-Modal Agent trained by an LLM from a Parallel TextWorldCode1
A Bayesian Approach to Robust Inverse Reinforcement LearningCode1
Show:102550
← PrevPage 3 of 43Next →

No leaderboard results yet.