Timezone: »
The Emergence of Abstract and Episodic Neurons in Episodic Meta-RL
Badr AlKhamissi · Muhammad ElNokrashy · Michael Spranger
Event URL: https://openreview.net/forum?id=EmH6CgI6RO »
In this work, we analyze the reinstatement mechanism introduced by Ritter et al. (2018) to reveal two classes of neurons that emerge in the agent's working memory (an epLSTM cell) when trained using episodic meta-RL on an episodic variant of the Harlow visual fixation task. Specifically, Abstract neurons encode knowledge shared across tasks, while Episodic neurons carry information relevant for a specific episode's task.
Author Information
Badr AlKhamissi (Meta AI)
Muhammad ElNokrashy (Microsoft)
Michael Spranger (Sony)
Related Events (a corresponding poster, oral, or spotlight)
-
2022 : The Emergence of Abstract and Episodic Neurons in Episodic Meta-RL »
Fri. Dec 2nd 04:15 -- 04:20 PM Room
More from the Same Authors
-
2022 : MocoSFL: enabling cross-client collaborative self-supervised learning »
Jingtao Li · Lingjuan Lyu · Daisuke Iso · Chaitali Chakrabarti · Michael Spranger -
2022 : Depth-Wise Attention (DWAtt): A Layer Fusion Method for Data-Efficient Classification »
Muhammad ElNokrashy · Badr AlKhamissi · Mona Diab -
2022 : Feasible and Desirable Counterfactual Generation by Preserving Human Defined Constraints »
Homayun Afrabandpey · Michael Spranger -
2022 Poster: Outsourcing Training without Uploading Data via Efficient Collaborative Open-Source Sampling »
Junyuan Hong · Lingjuan Lyu · Jiayu Zhou · Michael Spranger -
2020 Poster: Assessing SATNet's Ability to Solve the Symbol Grounding Problem »
Oscar Chang · Lampros Flokas · Hod Lipson · Michael Spranger -
2020 Expo Talk Panel: Hypotheses Generation for Applications in Biomedicine and Gastronomy »
Michael Spranger · Kosuke Aoki