Meta-Reinforcement Learning by Tracking Task Non-stationarity

被引:0
|
作者
Poiani, Riccardo [1 ]
Tirinzoni, Andrea [2 ]
Restelli, Marcello [1 ]
机构
[1] Politecn Milan, Milan, Italy
[2] Inria Lille, Lille, France
关键词
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Many real-world domains are subject to a structured non-stationarity which affects the agent's goals and the environmental dynamics. Meta-reinforcement learning (RL) has been shown successful for training agents that quickly adapt to related tasks. However, most of the existing meta-RL algorithms for non-stationary domains either make strong assumptions on the task generation process or require sampling from it at training time. In this paper, we propose a novel algorithm (TRIO) that optimizes for the future by explicitly tracking the task evolution through time. At training time, TRIO learns a variational module to quickly identify latent parameters from experience samples. This module is learned jointly with an optimal exploration policy that takes task uncertainty into account. At test time, TRIO tracks the evolution of the latent parameters online, hence reducing the uncertainty over future tasks and obtaining fast adaptation through the meta-learned policy. Unlike most existing methods, TRIO does not assume Markovian task-evolution processes, it does not require information about the non-stationarity at training time, and it captures complex changes undergoing in the environment. We evaluate our algorithm on different simulated problems and show it outperforms competitive baselines.
引用
收藏
页码:2899 / 2905
页数:7
相关论文
共 50 条
  • [31] Meta-Reinforcement Learning With Dynamic Adaptiveness Distillation
    Hu, Hangkai
    Huang, Gao
    Li, Xiang
    Song, Shiji
    IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2023, 34 (03) : 1454 - 1464
  • [32] Zero-Shot Policy Transfer with Disentangled Task Representation of Meta-Reinforcement Learning
    Wu, Zheng
    Xie, Yichen
    Lian, Wenzhao
    Wang, Changhao
    Guo, Yanjiang
    Chen, Jianyu
    Schaal, Stefan
    Tomizuka, Masayoshi
    2023 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA 2023), 2023, : 7169 - 7175
  • [33] Multiagent Meta-Reinforcement Learning for Optimized Task Scheduling in Heterogeneous Edge Computing Systems
    Niu, Liwen
    Chen, Xianfu
    Zhang, Ning
    Zhu, Yongdong
    Yin, Rui
    Wu, Celimuge
    Cao, Yangjie
    IEEE INTERNET OF THINGS JOURNAL, 2023, 10 (12) : 10519 - 10531
  • [34] A Meta-Reinforcement Learning Algorithm for Causal Discovery
    Sauter, Andreas
    Acar, Erman
    Francois-Lavet, Vincent
    CONFERENCE ON CAUSAL LEARNING AND REASONING, VOL 213, 2023, 213 : 602 - 619
  • [35] Formalising Performance Guarantees in Meta-Reinforcement Learning
    Mahony, Amanda
    FORMAL METHODS AND SOFTWARE ENGINEERING, ICFEM 2018, 2018, 11232 : 469 - 472
  • [36] Meta-reinforcement learning via orbitofrontal cortex
    Hattori, Ryoma
    Hedrick, Nathan G.
    Jain, Anant
    Chen, Shuqi
    You, Hanjia
    Hattori, Mariko
    Choi, Jun-Hyeok
    Lim, Byung Kook
    Yasuda, Ryohei
    Komiyama, Takaki
    NATURE NEUROSCIENCE, 2023, 26 (12) : 2182 - 2191
  • [37] Context meta-reinforcement learning via neuromodulation
    Ben-Iwhiwhu, Eseoghene
    Dick, Jeffery
    Ketz, Nicholas A.
    Pilly, Praveen K.
    Soltoggio, Andrea
    NEURAL NETWORKS, 2022, 152 : 70 - 79
  • [38] Meta-Reinforcement Learning via Language Instructions
    Bing, Zhenshan
    Koch, Alexander
    Yao, Xiangtong
    Huang, Kai
    Knoll, Alois
    2023 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION, ICRA, 2023, : 5985 - 5991
  • [39] Meta-Reinforcement Learning in Nonstationary and Nonparametric Environments
    Bing, Zhenshan
    Knak, Lukas
    Cheng, Long
    Morin, Fabrice O.
    Huang, Kai
    Knoll, Alois
    IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2024, 35 (10) : 13604 - 13618
  • [40] Offline Meta-Reinforcement Learning with Advantage Weighting
    Mitchell, Eric
    Rafailov, Rafael
    Peng, Xue Bin
    Levine, Sergey
    Finn, Chelsea
    INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 139, 2021, 139