Interactive reinforcement learning (IRL) agents use human feedback or instruction to help them learn in complex environments. Often, this feedback comes in the form of a discrete signal that’s either positive or negative. While informative, this information can be difficult to generalize on its own. In this work, we explore how natural language advice can be used to provide a richer feedback signal to a reinforcement learning agent by extending policy shaping, a well-known IRL technique. Usually policy shaping employs a human feedback policy to help an agent to learn more about how to achieve its goal. In our case, we replace this human feedback policy with policy generated based on natural language advice. We aim to inspect if the generated natural language reasoning provides support to a deep RL agent to decide its actions successfully in any given environment. So, we design our model with three networks: first one is the experience driven, next is the advice generator and third one is the advice driven. While the experience driven RL agent chooses its actions being influenced by the environmental reward, the advice driven neural network with generated feedback by the advice generator for any new state selects its actions to assist the RL agent to better policy shaping.


    Access

    Download


    Export, share and cite



    Title :

    Influencing Reinforcement Learning through Natural Language Guidance


    Contributors:

    Publication date :

    2021-04-18


    Remarks:

    doi:10.32473/flairs.v34i1.128472
    The International FLAIRS Conference Proceedings; Vol 34 (2021): Proceedings of FLAIRS-34 ; 2334-0762 ; 10.32473/flairs.v34i1



    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English


    Classification :

    DDC:    629




    Influencing Reinforcement Learning through Natural Language Guidance

    Tasrin, Tasmia / Nahian, Md Sultan Al / Perera, Habarakadage et al. | BASE | 2021

    Free access

    Tethered Multicopter Guidance in GPS-Denied Environments Through Reinforcement Learning

    Al-Radaideh, Amer / Selje, Robert A. / Coraspe, Daniel et al. | TIBKAT | 2023



    Tethered Multicopter Guidance in GPS-Denied Environments Through Reinforcement Learning

    Al-Radaideh, Amer / Selje, Robert A. / Coraspe, Daniel et al. | AIAA | 2023


    Adaptive Guidance with Reinforcement Meta Learning

    Gaudet, Brian / Linares, Richard | TIBKAT | 2019