1 code implementation • 21 Jan 2023 • Andrea Soltoggio, Eseoghene Ben-Iwhiwhu, Christos Peridis, Pawel Ladosz, Jeffery Dick, Praveen K. Pilly, Soheil Kolouri
This paper introduces a set of formally defined and transparent problems for reinforcement learning algorithms with the following characteristics: (1) variable degrees of observability (non-Markov observations), (2) distal and sparse rewards, (3) variable and hierarchical reward structure, (4) multiple-task generation, (5) variable problem complexity.
1 code implementation • 30 Oct 2021 • Eseoghene Ben-Iwhiwhu, Jeffery Dick, Nicholas A. Ketz, Praveen K. Pilly, Andrea Soltoggio
Meta-reinforcement learning (meta-RL) algorithms enable agents to adapt quickly to tasks from few samples in dynamic environments.
no code implementations • 29 Sep 2021 • Ali Geisa, Ronak Mehta, Hayden S. Helm, Jayanta Dey, Eric Eaton, Jeffery Dick, Carey E. Priebe, Joshua T. Vogelstein
This assumption renders these theories inadequate for characterizing 21$^{st}$ century real world data problems, which are typically characterized by evaluation distributions that differ from the training data distributions (referred to as out-of-distribution learning).
1 code implementation • 27 Apr 2020 • Eseoghene Ben-Iwhiwhu, Pawel Ladosz, Jeffery Dick, Wen-Hua Chen, Praveen Pilly, Andrea Soltoggio
Rapid online adaptation to changing tasks is an important problem in machine learning and, recently, a focus of meta-reinforcement learning.
1 code implementation • 21 Sep 2019 • Pawel Ladosz, Eseoghene Ben-Iwhiwhu, Jeffery Dick, Yang Hu, Nicholas Ketz, Soheil Kolouri, Jeffrey L. Krichmar, Praveen Pilly, Andrea Soltoggio
This paper presents a new neural architecture that combines a modulated Hebbian network (MOHN) with DQN, which we call modulated Hebbian plus Q network architecture (MOHQA).