{"total":16,"rows":[{"id":"2102.06858","title":"LTL2Action: Generalizing LTL Instructions for Multi-Task RL","created":"2021-02-13","cited_by_count":74,"area":null},{"id":"2211.10902","title":"Noisy Symbolic Abstractions for Deep RL: A case study with Reward Machines","created":"2022-11-20","cited_by_count":10,"area":null},{"id":"2212.03181","title":"Funnel-based Reward Shaping for Signal Temporal Logic Tasks in Reinforcement Learning","created":"2022-11-30","cited_by_count":8,"area":null},{"id":"2110.02792","title":"Hierarchical Potential-based Reward Shaping from Task Specifications","created":"2021-10-06","cited_by_count":7,"area":null},{"id":"2202.02404","title":"Model-Free Reinforcement Learning for Symbolic Automata-encoded Objectives","created":"2022-02-04","cited_by_count":6,"area":null},{"id":"2203.12686","title":"Possibility Before Utility: Learning And Using Hierarchical Affordances","created":"2022-03-23","cited_by_count":4,"area":null},{"id":"2212.01022","title":"STL-Based Synthesis of Feedback Controllers Using Reinforcement Learning","created":"2022-12-02","cited_by_count":4,"area":null},{"id":"2301.02952","title":"Learning Symbolic Representations for Reinforcement Learning of Non-Markovian Behavior","created":"2023-01-08","cited_by_count":4,"area":null},{"id":"2103.12558","title":"Assured Learning-enabled Autonomy: A Metacognitive Reinforcement Learning Framework","created":"2021-03-23","cited_by_count":3,"area":null},{"id":"2103.15938","title":"Safe Model-based Control from Signal Temporal Logic Specifications Using Recurrent Neural Networks","created":"2021-03-29","cited_by_count":3,"area":null},{"id":"2108.01317","title":"Deep Reinforcement Learning Based Networked Control with Network Delays for Signal Temporal Logic Specifications","created":"2021-08-03","cited_by_count":1,"area":null},{"id":"2212.05200","title":"Neural Controller Synthesis for Signal Temporal Logic Specifications Using Encoder-Decoder Structured Networks","created":"2022-12-10","cited_by_count":1,"area":null},{"id":"2307.06758","title":"Layered controller synthesis for dynamic multi-agent systems","created":"2023-07-13","cited_by_count":1,"area":null},{"id":"2311.02099","title":"A Safe Preference Learning Approach for Personalization with Applications to Autonomous Vehicles","created":"2023-10-30","cited_by_count":1,"area":null},{"id":"2210.11259","title":"Safe Policy Improvement in Constrained Markov Decision Processes","created":"2022-10-20","cited_by_count":0,"area":null},{"id":"2304.12508","title":"Fulfilling Formal Specifications ASAP by Model-free Reinforcement Learning","created":"2023-04-25","cited_by_count":0,"area":null}],"next_cursor":null}