mlsanityData to 7 Oct 2026

MobILE: Model-Based Imitation Learning From Observation Alone

arXiv 2102.10769 ↗First posted 22 Feb 2021cs.LG stat.MLcited by 44

On the map: Offline RL and imitation learning from data → Imitation learning methods

Abstract (arXiv)

This paper studies Imitation Learning from Observations alone (ILFO) where the learner is presented with expert demonstrations that consist only of states visited by an expert (without access to actions taken by the expert). We present a provably efficient model-based framework MobILE to solve the ILFO problem. MobILE involves carefully trading off strategic exploration against imitation - this is achieved by integrating the idea of optimism in the face of uncertainty into the distribution matching imitation learning (IL) framework. We provide a unified analysis for MobILE, and demonstrate that MobILE enjoys strong performance guarantees for classes of MDP dynamics that satisfy certain well studied notions of structural complexity. We also show that the ILFO problem is strictly harder than the standard IL problem by presenting an exponential sample complexity separation between IL and ILFO. We complement these theoretical results with experimental simulations on benchmark OpenAI Gym tasks that indicate the efficacy of MobILE. Code for implementing the MobILE framework is available at https://github.com/rahulkidambi/MobILE-NeurIPS2021.

Key facts. Cited by 44 papers in the map (data through 7 Oct 2026). Placed in Imitation learning methods, one of 13 directions in Offline RL and imitation learning from data. Builds on 35 of its 72 references that are in the map. First posted on arXiv 22 Feb 2021.

Builds on

35 of 72 references.

Closest ancestors · 7

Same direction, newest first

  1. 2019A Divergence Minimization Perspective on Imitation Learning Methods6 Nov
  2. 2019Imitation Learning from Observations by Minimizing Inverse Dynamics Disagreement10 Oct
  3. 2019Imitation Learning as f-Divergence Minimization30 May
  4. 2019Provably Efficient Imitation Learning from Observation Alone27 May
  5. 2018Generative Adversarial Imitation from Observation17 Jul
  6. 2018Imitating Latent Policies from Observation21 May
  7. 2018Behavioral Cloning from Observation4 May

Other references · 28

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,635
  3. 2015Trust Region Policy Optimizationcited by 2,503
  4. 2016Generative Adversarial Imitation Learningcited by 1,576
  5. 2018Exploration by Random Network Distillationcited by 966
  6. 2019When to Trust Your Model: Model-Based Policy Optimizationcited by 753
  7. 2020MOReL : Model-Based Offline Reinforcement Learningcited by 582
  8. 2017Minimax Regret Bounds for Reinforcement Learningcited by 500
  9. 2016Guided Cost Learning: Deep Inverse Optimal Control via Policy Optimizationcited by 400
  10. 2017Neural Network Dynamics for Model-Based Deep Reinforcement Learning with Model-Free Fine-Tuningcited by 288
  11. 2019Self-Supervised Exploration via Disagreementcited by 263
  12. 2013Learning to Optimize Via Posterior Samplingcited by 253
16 more
  1. 2018Randomized Prior Functions for Deep Reinforcement Learningcited by 218
  2. 2018Model-Ensemble Trust-Region Policy Optimizationcited by 214
  3. 2019Reinforcement Learning in Feature Space: Matrix Bandit, Kernels, and Regret Boundcited by 199
  4. 2019Benchmarking Model-Based Reinforcement Learningcited by 158
  5. 2016Continuous Deep Q-Learning with Model-based Accelerationcited by 149
  6. 2018Algorithmic Framework for Model-based Deep Reinforcement Learning with Theoretical Guaranteescited by 138
  7. 2014Model-based Reinforcement Learning and the Eluder Dimensioncited by 116
  8. 2018Plan Online, Learn Offline: Efficient Learning and Exploration via Model-Based Controlcited by 104
  9. 2018Playing hard exploration games by watching YouTubecited by 98
  10. 2020Information Theoretic Regret Bounds for Online Nonlinear Controlcited by 87
  11. 2020Efficient Model-Based Reinforcement Learning through Optimistic Policy Search and Planningcited by 83
  12. 2020Reinforcement Learning with Videos: Combining Offline Observations with Interactioncited by 80
  13. 2020A Game Theoretic Framework for Model Based Reinforcement Learningcited by 72
  14. 2018Efficient Exploration through Bayesian Deep Q-Networkscited by 67
  15. 2017Towards Generalization and Simplicity in Continuous Controlcited by 65
  16. 2020Provably Efficient Model-based Policy Adaptationcited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 8; 2023: 13; 2024: 11; 2025: 5; 2026: 6.

44 papers.

Sort:

By area:

  1. 2022Model-Based Imitation Learning for Urban Drivingcited by 149
  2. 2021Visual Adversarial Imitation Learning using Variational Modelscited by 42
  3. 2022Semi-Supervised Offline Reinforcement Learning with Action-Free Trajectoriescited by 27
  4. 2022LobsDICE: Offline Learning from Observation via Stationary Distribution Correction Estimationcited by 22
  5. 2022Planning for Sample Efficient Imitation Learningcited by 20
  6. 2023Efficient Preference-Based Reinforcement Learning Using Learned Dynamics Modelscited by 20
  7. 2023DITTO: Offline Imitation Learning with World Modelscited by 20
  8. 2023Survival Instinct in Offline Reinforcement Learningcited by 20
  9. 2022A Ranking Game for Imitation Learningcited by 18
  10. 2023MAHALO: Unifying Offline Reinforcement Learning and Imitation Learning from Observationscited by 18
  11. 2022Discriminator-Guided Model-Based Offline Imitation Learningcited by 17
  12. 2024From Words to Actions: Unveiling the Theoretical Underpinnings of LLM-Driven Autonomous Systemscited by 17
32 more
  1. 2024A Survey of Imitation Learning Methods, Environments and Metricscited by 16
  2. 2024Diffusing States and Matching Scores: A New Framework for Imitation Learningcited by 16
  3. 2023Learning from Visual Observation via Offline Pretrained State-to-Go Transformercited by 14
  4. 2023Guiding Online Reinforcement Learning with Action-Free Offline Pretrainingcited by 11
  5. 2023Adversarial Imitation Learning from Visual Observations using Latent Informationcited by 10
  6. 2023Imitation Learning from Observation with Automatic Discount Schedulingcited by 10
  7. 2024A Dual Approach to Imitation Learning from Observations with Offline Datasetscited by 10
  8. 2024Visually Robust Adversarial Imitation Learning from Videos with Contrastive Learningcited by 9
  9. 2023Imitation Learning from Observation through Optimal Transportcited by 7
  10. 2022Improved Policy Optimization for Online Imitation Learningcited by 6
  11. 2023Learning non-Markovian Decision-Making from State-only Sequencescited by 6
  12. 2025IL-SOAR : Imitation Learning with Soft Optimistic Actor cRiticcited by 5
  13. 2025Controlling Large Language Model with Latent Actionscited by 5
  14. 2025Efficient Imitation under Misspecificationcited by 4
  15. 2025Learning Equilibria from Data: Provably Efficient Multi-Agent Imitation Learningcited by 4
  16. 2024Explorative Imitation Learning: A Path Signature Approach for Continuous Environmentscited by 3
  17. 2024Overcoming Knowledge Barriers: Online Imitation Learning from Visual Observation with Pretrained World Modelscited by 2
  18. 2026Puzzle it Out: Local-to-Global World Model for Offline Multi-Agent Reinforcement Learningcited by 2
  19. 2023GAN-MPC: Training Model Predictive Controllers with Parameterized Cost Functions using Demonstrations from Non-identical Expertscited by 1
  20. 2024Tiny Reinforcement Learning for Quadruped Locomotion using Decision Transformerscited by 1
  21. 2024Continual Learning from Simulated Interactions via Multitask Prospective Rehearsal for Bionic Limb Behavior Modelingcited by 1
  22. 2026Towards Generalisable Imitation Learning Through Conditioned Transition Estimation and Online Behaviour Alignmentcited by 1
  23. 2026Multi-agent imitation learning with function approximation: Linear Markov games and beyondcited by 1
  24. 2026Zero-shot Imitation Learning by Latent Topology Mappingcited by 1
  25. 2022Some Supervision Required: Incorporating Oracle Policies in Reinforcement Learning via Epistemic Uncertainty Metricscited by 0
  26. 2023Exploration in Model-based Reinforcement Learning with Randomized Rewardcited by 0
  27. 2023Self-Supervised Adversarial Imitation Learningcited by 0
  28. 2024A Model-Based Approach for Improving Reinforcement Learning Efficiency Leveraging Expert Observationscited by 0
  29. 2024Representation Alignment from Human Feedback for Cross-Embodiment Reward Learning from Mixed-Quality Demonstrationscited by 0
  30. 2025Learning from Observation: A Survey of Recent Advancescited by 0
  31. 2026Latent Wasserstein Adversarial Imitation Learningcited by 0
  32. 2026Beyond Conservatism: Recoverability-Conditioned Exploration for Model-Based Imitation Learningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Efficient Imitation Learning with Conservative World Models
  2. 2025Imitation Learning in the Deep Learning Era: A Novel Taxonomy and Recent Advances
  3. 2025Value from Observations: Towards Large-Scale Imitation Learning via Self-Improvement
  4. 2020On the Guaranteed Almost Equivalence between Imitation Learning from Observation and Demonstration
  5. 2021Of Moments and Matching: A Game-Theoretic Framework for Closing the Imitation Gap
  6. 2023Provably Efficient Adversarial Imitation Learning with Unknown Transitions
  7. 2020State-only Imitation with Transition Dynamics Mismatch
  8. 2023Offline Imitation Learning with Suboptimal Demonstrations via Relaxed Distribution Matching