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 1751–1775 of 2122 papers

TitleStatusHype
Learning to request guidance in emergent language—0
Seeded self-play for language learning—0
Plan Arithmetic: Compositional Plan Vectors for Multi-Task Control—0
Learning a Safety Verifiable Adaptive Cruise Controller from Human Driving Data—0
Learning Latent Process from High-Dimensional Event Sequences via Efficient SamplingCode0
BAIL: Best-Action Imitation Learning for Batch Deep Reinforcement LearningCode0
Relay Policy Learning: Solving Long-Horizon Tasks via Imitation and Reinforcement LearningCode0
Optimal Power Flow Using Graph Neural NetworksCode1
Conditional Driving from Natural Language Instructions—0
Learning chordal extensions—0
Topological Navigation Graph Framework—0
Imitating by generating: deep generative models for imitation of interactive tasks—0
Imitation Learning from Observations by Minimizing Inverse Dynamics Disagreement—0
Model-based Behavioral Cloning with Future Image Similarity LearningCode0
Is a Good Representation Sufficient for Sample Efficient Reinforcement Learning?—0
Riemannian Motion Policy Fusion through Learnable Lyapunov Function Reshaping—0
Review of Learning-based Longitudinal Motion Planning for Autonomous Vehicles: Research Gaps between Self-driving and Traffic Congestion—0
Learning Calibratable Policies using Programmatic Style-ConsistencyCode0
Task-Relevant Adversarial Imitation Learning—0
INTERACTION Dataset: An INTERnational, Adversarial and Cooperative moTION Dataset in Interactive Driving Scenarios with Semantic Maps—0
Tensor-based Cooperative Control for Large Scale Multi-intersection Traffic Signal Using Deep Reinforcement Learning and Imitation Learning—0
Domain Adaptive Imitation LearningCode0
Zero-shot Imitation Learning from Demonstrations for Legged Robot Visual Navigation—0
RLBench: The Robot Learning Benchmark & Learning EnvironmentCode0
Imitation Learning of Robot Policies using Language, Vision and Motion—0
Show:102550
← PrevPage 71 of 85Next →

No leaderboard results yet.