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 1401–1425 of 2122 papers

TitleStatusHype
Benchmarking Sample Selection Strategies for Batch Reinforcement Learning—0
Learning the Representation of Behavior Styles with Imitation Learning—0
Transferring Hierarchical Structure with Dual Meta Imitation Learning—0
Automatic Discovery and Description of Human Planning StrategiesCode0
Auto-Encoding Inverse Reinforcement Learning—0
CrowdPlay: Crowdsourcing human demonstration data for offline learning in Atari games—0
Plan Your Target and Learn Your Skills: State-Only Imitation Learning via Decoupled Policy Optimization—0
Language Model Pre-training Improves Generalization in Policy Learning—0
Lagrangian Method for Episodic Learning—0
Lagrangian Generative Adversarial Imitation Learning with Safety—0
DemoDICE: Offline Imitation Learning with Supplementary Imperfect Demonstrations—0
Diverse Imitation Learning via Self-OrganizingGenerative Models—0
What Would the Expert do()?: Causal Imitation Learning—0
Imitation Learning from Pixel Observations for Continuous Control—0
SafetyNet: Safe planning for real-world self-driving vehicles using machine-learned policies—0
Learning to Superoptimize Real-world Programs—0
Bottom-Up Skill Discovery from Unsegmented Demonstrations for Long-Horizon Robot Manipulation—0
Dynamic Modeling of Hand-Object Interactions via Tactile Sensing.—0
Learning Relative Interactions through Imitation—0
Imitation Learning of Stabilizing Policies for Nonlinear SystemsCode0
Demonstration-Efficient Guided Policy Search via Imitation of Robust Tube MPC—0
ThriftyDAgger: Budget-Aware Novelty and Risk Gating for Interactive Imitation Learning—0
Deep Visual Navigation under Partial Observability—0
Reactive and Safe Road User Simulations using Neural Barrier CertificatesCode0
Cross Domain Robot Imitation with Invariant RepresentationCode0
Show:102550
← PrevPage 57 of 85Next →

No leaderboard results yet.