Publications

Download a PDF with the full list of our publications: Robot-Intelligence-Lab-Publications-2021.pdf

A comprehensive list can also be found at Google Scholar, or by searching for the publications of author Kormushev, Petar.

Citation

BibTex format

@inproceedings{Tavakoli:2018,
author = {Tavakoli, A and Pardo, F and Kormushev, P},
publisher = {AAAI},
title = {Action branching architectures for deep reinforcement learning},
url = {http://kormushev.com/papers/Tavakoli_AAAI-2018.pdf},
year = {2018}
}
Download

RIS format (EndNote, RefMan)

TY  - CPAPER
AB  - Discrete-action  algorithms  have  been  central  to  numerousrecent  successes  of  deep  reinforcement  learning.  However,applying  these  algorithms  to  high-dimensional  action  tasksrequires  tackling  the  combinatorial  increase  of  the  numberof  possible  actions  with  the  number  of  action  dimensions.This  problem  is  further  exacerbated  for  continuous-actiontasks  that  require  fine  control  of  actions  via  discretization.In  this  paper,  we  propose  a  novel  neural  architecture  fea-turing  a  shared  decision  module  followed  by  several  net-workbranches, one for each action dimension. This approachachieves a linear increase of the number of network outputswith the number of degrees of freedom by allowing a level ofindependence for each individual action dimension. To illus-trate the approach, we present a novel agent, called Branch-ing  Dueling  Q-Network  (BDQ),  as  a  branching  variant  ofthe Dueling Double Deep Q-Network (Dueling DDQN). Weevaluate the performance of our agent on a set of challeng-ing continuous control tasks. The empirical results show thatthe proposed agent scales gracefully to environments with in-creasing action dimensionality and indicate the significanceof  the  shared  decision  module  in  coordination  of  the  dis-tributed action branches. Furthermore, we show that the pro-posed  agent  performs  competitively  against  a  state-of-the-art continuous control algorithm, Deep Deterministic PolicyGradient (DDPG).
AU  - Tavakoli,A
AU  - Pardo,F
AU  - Kormushev,P
PB  - AAAI
PY  - 2018///
TI  - Action branching architectures for deep reinforcement learning
UR  - http://kormushev.com/papers/Tavakoli_AAAI-2018.pdf
UR  - http://hdl.handle.net/10044/1/60671
ER  -
Download