Zero-shot Imitation Policy via Search in Demonstration Dataset

no code implementations • 29 Jan 2024 • Federco Malato, Florian Leopold, Andrew Melnik, Ville Hautamaki

Behavioral cloning uses a dataset of demonstrations to learn a policy.

Imitation Learning

Behavioral Cloning via Search in Embedded Demonstration Dataset

no code implementations • 15 Jun 2023 • Federico Malato, Florian Leopold, Ville Hautamaki, Andrew Melnik

Actions from a selected similar situation can be performed by the agent until representations of the agent's current situation and the selected experience diverge in the latent space.

Behavioural cloning

Towards Solving Fuzzy Tasks with Human Feedback: A Retrospective of the MineRL BASALT 2022 Competition

no code implementations • 23 Mar 2023 • Stephanie Milani, Anssi Kanervisto, Karolis Ramanauskas, Sander Schulhoff, Brandon Houghton, Sharada Mohanty, Byron Galbraith, Ke Chen, Yan Song, Tianze Zhou, Bingquan Yu, He Liu, Kai Guan, Yujing Hu, Tangjie Lv, Federico Malato, Florian Leopold, Amogh Raut, Ville Hautamäki, Andrew Melnik, Shu Ishida, João F. Henriques, Robert Klassert, Walter Laurito, Ellen Novoseller, Vinicius G. Goecks, Nicholas Waytowich, David Watkins, Josh Miller, Rohin Shah

To facilitate research in the direction of fine-tuning foundation models from human feedback, we held the MineRL BASALT Competition on Fine-Tuning from Human Feedback at NeurIPS 2022.

Behavioral Cloning via Search in Video PreTraining Latent Space

no code implementations • 27 Dec 2022 • Federico Malato, Florian Leopold, Amogh Raut, Ville Hautamäki, Andrew Melnik

Our approach can effectively recover meaningful demonstration trajectories and show human-like behavior of an agent in the Minecraft environment.

Imitation Learning