{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/deep-episodic-memory-encoding-recalling-and","title":"Deep Episodic Memory: Encoding, Recalling, and Predicting Episodic Experiences for Robot Action Execution","arxiv_id":"1801.04134","date":"2018-01-12","proceeding":null,"authors":["Jonas Rothfuss","Fabio Ferreira","Eren Erdal Aksoy","You Zhou","Tamim Asfour"],"abstract":"We present a novel deep neural network architecture for representing robot\nexperiences in an episodic-like memory which facilitates encoding, recalling,\nand predicting action experiences. Our proposed unsupervised deep episodic\nmemory model 1) encodes observed actions in a latent vector space and, based on\nthis latent encoding, 2) infers most similar episodes previously experienced,\n3) reconstructs original episodes, and 4) predicts future frames in an\nend-to-end fashion. Results show that conceptually similar actions are mapped\ninto the same region of the latent vector space. Based on these results, we\nintroduce an action matching and retrieval mechanism, benchmark its performance\non two large-scale action datasets, 20BN-something-something and ActivityNet\nand evaluate its generalization capability in a real-world scenario on a\nhumanoid robot.","url_abs":"http://arxiv.org/abs/1801.04134v3","url_pdf":"http://arxiv.org/pdf/1801.04134v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"deep-episodic-memory-encoding-recalling-and","repo_url":"https://github.com/jonasrothfuss/DeepEpisodicMemory","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}