Attention-based Curiosity in Multi-agent Reinforcement Learning Environments

Abstract

Several paradigms exist in Reinforcement Learning to improve the exploration capabilities of agents, among which the curiosity-driven approach is followed in this work. Extending previous work that utilizes attention to make curiosity state-and action-selective, we expand the range of experiments by introducing two multi-agent environments. The first one is for robot soccer, the second one features a driving scenario in urban settings. Moreover, as during training the different number of observations must be matched between multiple time-steps, we propose an attention-based approach, called Recurrent Temporal Attention (RTA) to do this. The corresponding implementation can be found at https://github.com/szemenyeim/DynEnv.

Citation

M. Szemenyei and P. Reizinger, “Attention-Based Curiosity in Multi-Agent Reinforcement Learning Environments,” 2019 International Conference on Control, Artificial Intelligence, Robotics & Optimization (ICCAIRO), 2019, pp. 176-181, doi: 10.1109/ICCAIRO47923.2019.00035.

@INPROCEEDINGS{szemenyei2019dynenv,  
    author={Szemenyei, Márton and Reizinger, Patrik},  
    booktitle={2019 International Conference on Control, Artificial Intelligence, Robotics   Optimization (ICCAIRO)},   
    title={Attention-Based Curiosity in Multi-Agent Reinforcement Learning Environments},   
    year={2019},  
    volume={},  
    number={},  
    pages={176-181},  
    doi={10.1109/ICCAIRO47923.2019.00035}
}