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 1201–1250 of 2122 papers

TitleStatusHype
SCC: an efficient deep reinforcement learning agent mastering the game of StarCraft II—0
SCIZOR: A Self-Supervised Approach to Data Curation for Large-Scale Imitation Learning—0
SculptDiff: Learning Robotic Clay Sculpting from Humans with Goal Conditioned Diffusion Policy—0
SDA: Improving Text Generation with Self Data Augmentation—0
SE(3)-Equivariant Robot Learning and Control: A Tutorial Survey—0
SEAL: SEmantic-Augmented Imitation Learning via Language Model—0
Searching for Objects using Structure in Indoor Scenes—0
Seeded self-play for language learning—0
Seeing Differently, Acting Similarly: Heterogeneously Observable Imitation Learning—0
SEIHAI: A Sample-efficient Hierarchical AI for the MineRL Competition—0
Selective Eye-gaze Augmentation To Enhance Imitation Learning In Atari Games—0
Selective Sampling and Imitation Learning via Online Regression—0
Self-driven Grounding: Large Language Model Agents with Automatical Language-aligned Skill Learning—0
Self-Imitation Advantage Learning—0
Self-Imitation Learning by Planning—0
Self-Imitation Learning from Demonstrations—0
Self-Imitation Learning via Generalized Lower Bound Q-learning—0
Self-Imitation Learning via Trajectory-Conditioned Policy for Hard-Exploration Tasks—0
Self-Motivated Communication Agent for Real-World Vision-Dialog Navigation—0
Self-reconfiguration Strategies for Space-distributed Spacecraft—0
Self-Supervised Cross-View Correspondence with Predictive Cycle Consistency—0
Self-Supervised Disentangled Representation Learning for Third-Person Imitation Learning—0
SeMAIL: Eliminating Distractors in Visual Imitation via Separated Models—0
Semi-Supervised Imitation Learning of Team Policies from Suboptimal Demonstrations—0
Semi-Supervised One-Shot Imitation Learning—0
SENSOR: Imitate Third-Person Expert's Behaviors via Active Sensoring—0
SequenceMatch: Imitation Learning for Autoregressive Sequence Modelling with Backtracking—0
Sequential Causal Imitation Learning with Unobserved Confounders—0
Shaping Rewards for Reinforcement Learning with Imperfect Demonstrations using Generative Models—0
Shared Multi-Task Imitation Learning for Indoor Self-Navigation—0
SHEF-MIME: Word-level Quality Estimation Using Imitation Learning—0
SIMILE: Introducing Sequential Information towards More Effective Imitation Learning—0
Sim-to-Real Transfer in Deep Reinforcement Learning for Robotics: a Survey—0
Simultaneously Learning Vision and Feature-based Control Policies for Real-world Ball-in-a-Cup—0
Simultaneous Translation with Flexible Policy via Restricted Imitation Learning—0
Single-Reset Divide & Conquer Imitation Learning—0
Situated GAIL: Multitask imitation using task-conditioned adversarial inverse reinforcement learning—0
Skeletal Feature Compensation for Imitation Learning with Embodiment Mismatch—0
Sketch-to-Skill: Bootstrapping Robot Learning with Human Drawn Trajectory Sketches—0
SKILL-IL: Disentangling Skill and Knowledge in Multitask Imitation Learning—0
SkillMimicGen: Automated Demonstration Generation for Efficient Skill Learning and Deployment—0
SKIL: Semantic Keypoint Imitation Learning for Generalizable Data-efficient Manipulation—0
SMART: Self-supervised Multi-task pretrAining with contRol Transformers—0
Smooth Imitation Learning via Smooth Costs and Smooth Policies—0
On the Sample Complexity of Imitation Learning for Smoothed Model Predictive Control—0
Socially Compliant Navigation Dataset (SCAND): A Large-Scale Dataset of Demonstrations for Social Navigation—0
Socially Guided Intrinsic Motivation for Robot Learning of Motor Skills—0
Social Motion Prediction with Cognitive Hierarchies—0
SoftCTRL: Soft conservative KL-control of Transformer Reinforcement Learning for Autonomous Driving—0
SoftDICE for Imitation Learning: Rethinking Off-policy Distribution Matching—0
Show:102550
← PrevPage 25 of 43Next →

No leaderboard results yet.