{"total":13,"rows":[{"id":"2206.06614","title":"Transformers are Meta-Reinforcement Learners","created":"2022-06-14","cited_by_count":41,"area":null},{"id":"2105.14039","title":"Towards mental time travel: a hierarchical memory for reinforcement learning agents","created":"2021-05-28","cited_by_count":40,"area":null},{"id":"2107.06011","title":"Teaching Agents how to Map: Spatial Reasoning for Multi-Object Navigation","created":"2021-07-13","cited_by_count":17,"area":null},{"id":"2309.14970","title":"Recurrent Hypernetworks are Surprisingly Strong in Meta-RL","created":"2023-09-26","cited_by_count":16,"area":null},{"id":"2402.19161","title":"MemoNav: Working Memory Model for Visual Navigation","created":"2024-02-29","cited_by_count":13,"area":null},{"id":"2302.07350","title":"Graph schemas as abstractions for transfer learning, inference, and planning","created":"2023-02-14","cited_by_count":7,"area":null},{"id":"2204.01437","title":"Disentangling Abstraction from Statistical Pattern Matching in Human and Machine Learning","created":"2022-04-04","cited_by_count":6,"area":null},{"id":"2210.02617","title":"Generalization Properties of Retrieval-based Models","created":"2022-10-06","cited_by_count":5,"area":null},{"id":"2211.03011","title":"On learning history based policies for controlling Markov decision processes","created":"2022-11-06","cited_by_count":5,"area":null},{"id":"2411.08447","title":"Learning Dynamic Cognitive Map with Autonomous Navigation","created":"2024-11-13","cited_by_count":3,"area":null},{"id":"2112.08360","title":"How to Learn and Represent Abstractions: An Investigation using Symbolic Alchemy","created":"2021-12-14","cited_by_count":1,"area":null},{"id":"2208.09610","title":"MemoNav: Selecting Informative Memories for Visual Navigation","created":"2022-08-20","cited_by_count":1,"area":null},{"id":"2303.07397","title":"Fast exploration and learning of latent graphs with aliased observations","created":"2023-03-13","cited_by_count":0,"area":null}],"next_cursor":null}