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 1026–1050 of 2122 papers

TitleStatusHype
Mimicking Better by Matching the Approximate Action DistributionCode0
Learning Space-Time Semantic Correspondences—0
Residual Q-Learning: Offline and Online Policy Customization without Value—0
Predictive Maneuver Planning with Deep Reinforcement Learning (PMP-DRL) for comfortable and safe autonomous driving—0
Unraveling the ARC Puzzle: Mimicking Human Solutions with Object-Centric Decision Transformer—0
Learning to Stabilize High-dimensional Unknown Systems Using Lyapunov-guided ExplorationCode0
Skill Disentanglement for Imitation Learning from Suboptimal DemonstrationsCode0
Reinforcement Learning in Robotic Motion Planning by Combined Experience-based Planning and Self-Imitation Learning—0
Provably Efficient Adversarial Imitation Learning with Unknown TransitionsCode0
PEAR: Primitive enabled Adaptive Relabeling for boosting Hierarchical Reinforcement Learning—0
Transferring Foundation Models for Generalizable Robotic Manipulation—0
SequenceMatch: Imitation Learning for Autoregressive Sequence Modelling with Backtracking—0
Divide and Repair: Using Options to Improve Performance of Imitation Learning Against Adversarial Demonstrations—0
Data Quality in Imitation Learning—0
On the Sample Complexity of Imitation Learning for Smoothed Model Predictive Control—0
PAGAR: Taming Reward Misalignment in Inverse Reinforcement Learning-Based Imitation Learning with Protagonist Antagonist Guided Adversarial Reward—0
Causal Imitability Under Context-Specific Independence Relations—0
GAN-MPC: Training Model Predictive Controllers with Parameterized Cost Functions using Demonstrations from Non-identical Experts—0
What is Essential for Unseen Goal Generalization of Offline Goal-conditioned RL?Code0
Language-Conditioned Imitation Learning with Base Skill Priors under Unstructured Data—0
How To Not Train Your Dragon: Training-free Embodied Object Goal Navigation with Semantic Frontiers—0
Neural Task Synthesis for Visual ProgrammingCode0
Emergent Agentic Transformer from Chain of Hindsight Experience—0
Imitating Task and Motion Planning with Visuomotor Transformers—0
Asking Before Acting: Gather Information in Embodied Decision Making with Language Models—0
Show:102550
← PrevPage 42 of 85Next →

No leaderboard results yet.