Provably Efficient Third-Person Imitation from Offline Observation
On the map: Offline RL and imitation learning from data → Imitation learning methods
Abstract (arXiv)
Domain adaptation in imitation learning represents an essential step towards improving generalizability. However, even in the restricted setting of third-person imitation where transfer is between isomorphic Markov Decision Processes, there are no strong guarantees on the performance of transferred policies. We present problem-dependent, statistical learning guarantees for third-person imitation from observation in an offline setting, and a lower bound on performance in the online setting.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Imitation learning methods, one of 13 directions in Offline RL and imitation learning from data. First posted on arXiv 27 Feb 2020.
Builds on
No reference list yet.
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2024Online Adaptation for Enhancing Imitation Learning Policies
- 2023Domain Adaptive Imitation Learning with Visual Observation
- 2021Cross-domain Imitation from Observations
- 2025Using Non-Expert Data to Robustify Imitation Learning via Offline Reinforcement Learning
- 2023A Simple Solution for Offline Imitation from Observations and Examples with Possibly Incomplete Trajectories
- 2025A Recipe for Efficient Sim-to-Real Transfer in Manipulation with Online Imitation-Pretrained World Models
- 2019Domain Adaptive Imitation Learning
- 2021Mitigating Covariate Shift in Imitation Learning via Offline Data Without Great Coverage