Imitation Learning: A Survey of Learning Methods, Environments and Metrics
By Nathan Gavenski, Odinaldo Rodrigues, Michael Luck. arXiv.org, 2024
535 citations recorded by the source corpus.
Subfields: Computer Vision and Pattern Recognition, Control and Systems Engineering, Social Psychology
View Paper: https://www.semanticscholar.org/paper/70987dd4fb41109c723bcff127818870662aa108
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
- Qin Liu
- Marc Niethammer
- Terrence Chen
- Srikrishna Karanam
- Meng Zheng
- Ziyan Wu
- Benjamin Planche
- Jitendra Malik
Citations in the corpus
- Tool Learning with Foundation Models (2023, unknown): “Models can be trained to mimic the behavior of human experts through imitation learning (Hussein et al., 2017; Liu et al., 2018b; Baker et al., 2022).”
- Principled Reinforcement Learning with Human Feedback from Pairwise or K-wise Comparisons (2023, unknown): “…imitation learning, we only observe an expert’s behavior and would like to infer the expert’s preferences or goals (Ng et al., 2000; Abbeel and Ng, 2004; Ziebart et al., 2008; Ramachandran and Amir, 2007; Neu and Szepesv´ari, 2009; Ho and Ermon, 2016; Florence et al., 2022; Hussein et al., 2017).”
- PseudoClick: Interactive Image Segmentation with Click Imitation (2022, background): “Imitation learning techniques aim to mimic human behavior for a given task [25].”
- A Survey of Imitation Learning Methods, Environments and Metrics (2024, unknown): “These new metrics and environments, along with other surveys [47, 105, 121] focusing more on learning techniques, create a lack of standardisation in the evaluation process, making meaningful comparisons between different approaches challenging.”
- Cognitive Architectures for Language Agents (2023, unknown): “Such fine-tuning can be accomplished via supervised or imitation learning (Hussein et al., 2017), reinforcement learning (RL) from environment feedback (Sutton and Barto, 2018), human feedback (RLHF) (Christiano et al.”
- A Survey of Imitation Learning: Algorithms, Recent Developments, and Challenges (2023, unknown): “While numerous surveys have been conducted on the IL over the years, there remains a need for a comprehensive overview that captures the latest developments in this rapidly evolving domain [1], [3], [6], [10].”