Research map / Reinforcement learning / Imitation learning
IOSTOM: Offline Imitation Learning from Observations via State Transition Occupancy Matching
Quang Anh Pham, Janaka Chathuranga Brahmanage, Tien Anh Mai, Akshat Kumar
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes IOSTOM, an offline learning-from-observations method that imitates expert behavior by matching state transition occupancy between expert state trajectories and suboptimal transition data.
Problem
Offline learning from observations (LfO), where an agent must imitate expert behavior using only expert state trajectories plus separate suboptimal transition data with actions, without environment interaction or expert action labels.
Approach
Instead of directly inferring actions for expert states, the method matches state transition occupancy between expert and agent data so that the policy reproduces expert-like state transitions using the offline transition data.
Experimental setup
Datasets: expert state trajectories suboptimal transition data
Closest papers by meaning
- Imitation from Observations with Trajectory-Level Generative Embeddings (NeurIPS 2026 · similarity 0.90)
- How to Leverage Diverse Demonstrations in Offline Imitation Learning (ICML 2024 · similarity 0.89)
- Diffusion Imitation from Observation (NeurIPS 2024 · similarity 0.89)
- Is Behavior Cloning All You Need? Understanding Horizon in Imitation Learning (NeurIPS 2024 · similarity 0.89)
- Offline Imitation from Observation via Primal Wasserstein State Occupancy Matching (ICML 2024 · similarity 0.89)
- Behavior Cloning is Not All You Need: The Optimality of On-Policy Distillation for Noisy Expert Feedback (NeurIPS 2026 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
