Long Horizon Episodic Decision Making for Cognitively Inspired Robots
Shweta Singh1, Vedant Ghatnekar2, Sudaman Katti3
1Shweta Singh, Department of Brain, Cognition and Computation Lab, IIIT, Hyderabad (Telangana), India.
2Vedant Ghatnekar, Department of Mechanical Engineering, MIT WPU, Pune (Maharashtra), India.
3Sudaman Katti, Department of Mechanical Engineering, MIT WPU, Pune (Maharashtra), India.
Manuscript received on 01 December 2023 | Revised Manuscript received on 10 December 2024 | Manuscript Accepted on 15 February 2024 | Manuscript published on 28 February 2024 | PP: 1-7 | Volume-4 Issue-2, February 2024 | Retrieval Number: 100.1/ijainn.A108204011223 | DOI: 10.54105/ijainn.B1082.04020224
Open Access | Editorial and Publishing Policies | Cite | Zenodo | OJS | Indexing and Abstracting
© The Authors. Published by Lattice Science Publication (LSP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: The Human decision-making process works by recollecting past sequences of observations and using them to decide the best possible action in the present. These past sequences of observations are stored in a derived form which only includes important information the brain thinks might be useful in the future, while forgetting the rest. we propose an architecture that tries to mimic the human brain and improve the memory efficiency of transformers by using a modified Transformer XL architecture which uses Automatic Chunking which only attendsto the relevant chunksin the transformer block. On top ofthis,we useForget Span which is technique to remove memories that do not contribute to learning. We also theorize the technique of Similarity based forgetting to remove repetitive memories. We test our model in various tasks that test the abilities required to perform well in a human-robot collaboration scenario.
Keywords: Robotics, Machine Vision and Scene Understanding, Reasoning Under Uncertainty
Scope of the Article: Mechanical Maintenance