Timezone: »
Policy gradient methods have shown success in learning control policies for high-dimensional dynamical systems. Their biggest downside is the amount of exploration they require before yielding high-performing policies. In a lifelong learning setting, in which an agent is faced with multiple consecutive tasks over its lifetime, reusing information from previously seen tasks can substantially accelerate the learning of new tasks. We provide a novel method for lifelong policy gradient learning that trains lifelong function approximators directly via policy gradients, allowing the agent to benefit from accumulated knowledge throughout the entire training process. We show empirically that our algorithm learns faster and converges to better policies than single-task and lifelong learning baselines, and completely avoids catastrophic forgetting on a variety of challenging domains.
Author Information
Jorge Mendez (University of Pennsylvania)
Boyu Wang (University of Western Ontario)
Eric Eaton (University of Pennsylvania)
More from the Same Authors
-
2022 Spotlight: Lightning Talks 2B-4 »
Feiyi Xiao · Amrutha Saseendran · Kwangho Kim · Keyu Yan · Changjian Shui · Guangxi Li · Shikun Li · Edward Kennedy · Man Zhou · Gezheng Xu · Ruilin Ye · Xiaobo Xia · Junjie Tang · Kathrin Skubch · Stefan Falkner · Hansong Zhang · Jose Zubizarreta · Huaying Fang · Xuanqiang Zhao · Jie Huang · Qi CHEN · Yibing Zhan · Jiaqi Li · Xin Wang · Ruibin Xi · Feng Zhao · Margret Keuper · Charles Ling · Shiming Ge · Chengjun Xie · Tongliang Liu · Tal Arbel · Chongyi Li · Danfeng Hong · Boyu Wang · Christian Gagné -
2022 Spotlight: On Learning Fairness and Accuracy on Multiple Subgroups »
Changjian Shui · Gezheng Xu · Qi CHEN · Jiaqi Li · Charles Ling · Tal Arbel · Boyu Wang · Christian Gagné -
2022 Poster: On Learning Fairness and Accuracy on Multiple Subgroups »
Changjian Shui · Gezheng Xu · Qi CHEN · Jiaqi Li · Charles Ling · Tal Arbel · Boyu Wang · Christian Gagné -
2022 Affinity Workshop: LatinX in AI »
Maria Luisa Santiago · Juan Banda · CJ Barberan · MIGUEL GONZALEZ-MENDOZA · Caio Davi · Sara Garcia · Jorge Diaz · Fanny Nina Paravecino · Carlos Miranda · Gissella Bejarano Nicho · Fabian Latorre · Andres Munoz Medina · Abraham Ramos · Laura Montoya · Isabel Metzger · Andres Marquez · Miguel Felipe Arevalo-Castiblanco · Jorge Mendez · Karla Caballero · Atnafu Lambebo Tonja · Germán Olivo · Karla Caballero Barajas · Francisco Zabala -
2019 Poster: Transfer Learning via Minimizing the Performance Gap Between Domains »
Boyu Wang · Jorge Mendez · Mingbo Cai · Eric Eaton -
2018 Poster: Lifelong Inverse Reinforcement Learning »
Jorge Mendez · Shashank Shivkumar · Eric Eaton