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 1051–1100 of 2122 papers

TitleStatusHype
Learning to Structure an Image with Few Colors and Beyond—0
Towards Informed Design and Validation Assistance in Computer Games Using Imitation Learning—0
Sequential Causal Imitation Learning with Unobserved Confounders—0
Causal Imitation Learning with Unobserved Confounders—0
Exploring the trade off between human driving imitation and safety for traffic simulation—0
Solving the Baby Intuitions Benchmark with a Hierarchically Bayesian Theory of MindCode0
Sequence Model Imitation Learning with Unobserved ContextsCode0
Understanding Adversarial Imitation Learning in Small Sample Regime: A Stage-coupled Analysis—0
See What the Robot Can't See: Learning Cooperative Perception for Visual NavigationCode0
Robot Policy Learning from Demonstration Using Advantage Weighting and Early Termination—0
Improved Policy Optimization for Online Imitation LearningCode0
Learning Soccer Juggling Skills with Layer-wise Mixture-of-ExpertsCode1
Robots Enact Malignant Stereotypes—0
Lagrangian Method for Q-Function Learning (with Applications to Machine Translation)—0
Discriminator-Weighted Offline Imitation Learning from Suboptimal DemonstrationsCode1
Resolving Copycat Problems in Visual Imitation Learning via Residual Action Prediction—0
A Few Expert Queries Suffices for Sample-Efficient RL with Resets and Linear Value Approximation—0
Inspector: Pixel-Based Automated Game Testing via Exploration, Detection, and InvestigationCode0
Learning to Prove Trigonometric Identities—0
Finding Fallen Objects Via Asynchronous Audio-Visual Integration—0
Learning to Accelerate Approximate Methods for Solving Integer Programming via Early FixingCode0
Planning with RL and episodic-memory behavioral priors—0
WebShop: Towards Scalable Real-World Web Interaction with Grounded Language AgentsCode2
Target-absent Human AttentionCode1
Discriminator-Guided Model-Based Offline Imitation Learning—0
Watch and Match: Supercharging Imitation with Regularized Optimal Transport—0
Learning energy-efficient driving behaviors by imitating experts—0
Learning To Cut By Looking Ahead: Cutting Plane Selection via Imitation Learning—0
Improving Policy Optimization with Generalist-Specialist LearningCode0
Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online VideosCode3
Fighting Fire with Fire: Avoiding DNN Shortcuts through Priming—0
Auto-Encoding Adversarial Imitation Learning—0
Imitation Learning for Generalizable Self-driving Policy with Sim-to-real TransferCode0
Latent Policies for Adversarial Imitation Learning—0
Imitate then Transcend: Multi-Agent Optimal Execution with Dual-Window Denoise PPO—0
Model-Based Imitation Learning Using Entropy Regularization of Model and Policy—0
Nocturne: a scalable driving benchmark for bringing multi-agent learning one step closer to the real worldCode2
Robust Imitation Learning against Variations in Environment DynamicsCode1
Learning Multi-Task Transferable Rewards via Variational Inverse Reinforcement Learning—0
A deep inverse reinforcement learning approach to route choice modeling with context-dependent rewardsCode1
Deep Reinforcement Learning for Exact Combinatorial Optimization: Learning to Branch—0
Silver-Bullet-3D at ManiSkill 2021: Learning-from-Demonstrations and Heuristic Rule-based Methods for Object ManipulationCode1
Case-Based Inverse Reinforcement Learning Using Temporal CoherenceCode0
Model-based Offline Imitation Learning with Non-expert Data—0
Precise Affordance Annotation for Egocentric Action Video Datasets—0
Optimal Solutions for Joint Beamforming and Antenna Selection: From Branch and Bound to Graph Neural Imitation Learning—0
Imitation Learning via Differentiable PhysicsCode1
Temporal Logic Imitation: Learning Plan-Satisficing Motion Policies from Demonstrations—0
Imitating Past Successes can be Very Suboptimal—0
Driving in Real Life with Inverse Reinforcement Learning—0
Show:102550
← PrevPage 22 of 43Next →

No leaderboard results yet.