Exploiting Transformer in Sparse Reward Reinforcement Learning for Interpretable Temporal Logic Motion Planning

被引:4
|
作者
Zhang, Hao [1 ]
Wang, Hao [1 ]
Kan, Zhen [1 ]
机构
[1] Univ Sci & Technol China, Dept Automat, Hefei 230026, Peoples R China
基金
中国国家自然科学基金;
关键词
Task analysis; Transformers; Robots; Reinforcement learning; Planning; Learning automata; Encoding; Linear temporal logic; motion planning; reinforcement learning;
D O I
10.1109/LRA.2023.3290511
中图分类号
TP24 [机器人技术];
学科分类号
080202 ; 1405 ;
摘要
Automaton based approaches have enabled robots to perform various complex tasks. However, most existing automaton based algorithms highly rely on the manually customized representation of states for the considered task, limiting its applicability in deep reinforcement learning algorithms. To address this issue, by incorporating Transformer into reinforcement learning, we develop a Double-Transformer-guided Temporal Logic framework (T2TL) that exploits the structural feature of Transformer twice, i.e., first encoding the LTL instruction via the Transformer module for efficient understanding of task instructions during the training and then encoding the context variable via the Transformer again for improved task performance. Particularly, the LTL instruction is specified by co-safe LTL. As a semantics-preserving rewriting operation, LTL progression is exploited to decompose the complex task into learnable sub-goals, which not only converts non-Markovian reward decision processes to Markovian ones, but also improves the sampling efficiency by simultaneous learning of multiple sub-tasks. An environment-agnostic LTL pre-training scheme is further incorporated to facilitate the learning of the Transformer module resulting in an improved representation of LTL. The simulation results demonstrate the effectiveness of the T2TL framework.
引用
收藏
页码:4831 / 4838
页数:8
相关论文
共 50 条
  • [1] Expansive Latent Planning for Sparse Reward Offline Reinforcement Learning
    Gieselmann, Robert
    Pokorny, Florian T.
    CONFERENCE ON ROBOT LEARNING, VOL 229, 2023, 229
  • [2] Modular Deep Reinforcement Learning for Continuous Motion Planning With Temporal Logic
    Cai, Mingyu
    Hasanbeig, Mohammadhosein
    Xiao, Shaoping
    Abate, Alessandro
    Kan, Zhen
    IEEE ROBOTICS AND AUTOMATION LETTERS, 2021, 6 (04) : 7973 - 7980
  • [3] Planning-integrated Policy for Efficient Reinforcement Learning in Sparse-reward Environments
    Wulur, Christoper
    Weber, Cornelius
    Wermter, Stefan
    2021 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2021,
  • [4] Planning with Q-Values in Sparse Reward Reinforcement Learning
    Lei, Hejun
    Weng, Paul
    Rojas, Juan
    Guan, Yisheng
    INTELLIGENT ROBOTICS AND APPLICATIONS (ICIRA 2022), PT I, 2022, 13455 : 603 - 614
  • [5] Linear temporal logic guided safe reinforcement learning
    Li B.-L.
    Cai M.-Y.
    Kan Z.
    Kongzhi yu Juece/Control and Decision, 2023, 38 (07): : 1835 - 1844
  • [6] Motion Planning Using Hyperproperties for Time Window Temporal Logic
    Bonnah, Ernest
    Nguyen, Luan
    Hoque, Khaza Anuarul
    IEEE ROBOTICS AND AUTOMATION LETTERS, 2023, 8 (08) : 4386 - 4393
  • [7] Funnel-Based Reward Shaping for Signal Temporal Logic Tasks in Reinforcement Learning
    Saxena, Naman
    Gorantla, Sandeep
    Jagtap, Pushpak
    IEEE ROBOTICS AND AUTOMATION LETTERS, 2024, 9 (02) : 1373 - 1379
  • [8] Reinforcement Learning with Reward Shaping and Hybrid Exploration in Sparse Reward Scenes
    Yang, Yulong
    Cao, Weihua
    Guo, Linwei
    Gan, Chao
    Wu, Min
    2023 IEEE 6TH INTERNATIONAL CONFERENCE ON INDUSTRIAL CYBER-PHYSICAL SYSTEMS, ICPS, 2023,
  • [9] Survey of Deep Reinforcement Learning for Motion Planning of Autonomous Vehicles
    Aradi, Szilard
    IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, 2022, 23 (02) : 740 - 759
  • [10] Motion Planning for 2-DOF Transformable Wheel Robots Using Reinforcement Learning
    Park, Inha
    Ryu, Sijun
    Won, Jeeho
    Yoon, Hyeungyu
    Kim, SangGyun
    Kim, Hwa Soo
    Seo, TaeWon
    IEEE ROBOTICS AND AUTOMATION LETTERS, 2024, 9 (11): : 10193 - 10200