PARAMETRIZED DEEP Q-NETWORKS LEARNING: PLAYING ONLINE BATTLE ARENA WITH DISCRETE-CONTINUOUS HYBRID ACTION SPACE

Keywords

Computer science, Reinforcement learning, Action (physics), Set (abstract data type), Space (punctuation)

References

• Stochastic Approximation and Recursive Algorithms and ApplicationsHarold J. Kushner, G. George Yin — 2003
• Playing Atari with Deep Reinforcement LearningVolodymyr Mnih, Koray Kavukcuoglu, David Silver — 2013
• A Stochastic Approximation MethodHerbert Robbins, Sutton Monro — 1951
• Algorithms for Reinforcement LearningCsaba Szepesvári — 2010
• Stochastic approximation with two time scalesVivek S. Borkar — 1997
• Reinforcement Learning: An IntroductionSutton, Richard S, Barto, Andrew G — 1998
• A Natural Policy GradientSham M. Kakade — 2001
• Human-level control through deep reinforcement learningVolodymyr Mnih, Koray Kavukcuoglu, David Silver — 2015
• The Arcade Learning Environment: An Evaluation Platform for General AgentsM. G. Bellemare, Y. Naddaf, J. Veness — 2012
• Policy Gradient Methods for Reinforcement Learning with Function ApproximationRichard S. Sutton, David McAllester, Satinder Singh — 1999
• Deep Reinforcement Learning with Double Q-LearningHado van Hasselt, Arthur Guez, David Silver — 2015
• Deterministic Policy Gradient AlgorithmsDavid Silver, Guy Lever, Nicolas Heess — 2014
• Dueling Network Architectures for Deep Reinforcement LearningZiyu Wang, Tom Schaul, Matteo Hessel — 2015
• Reinforcement Learning with Parameterized ActionsWarwick Masson, Pravesh Ranchod, George Konidaris — 2015
• Mastering the game of Go with deep neural networks and tree searchDavid Silver, Aja Huang, Chris J. Maddison — 2016
• Guided Policy Search as Approximate Mirror DescentWilliam Montgomery, Sergey Levine — 2016
• Playing FPS Games with Deep Reinforcement LearningGuillaume Lample, Devendra Singh Chaplot — 2016
• PGQ: Combining policy gradient and Q-learningBrendan O’Donoghue, Rémi Munos, Koray Kavukcuoglu — 2016
• Playing Doom with SLAM-Augmented Deep Reinforcement LearningShehroze Bhatti, Alban Desmaison, Ondrej Miksik — 2016
• Stabilising Experience Replay for Deep Multi-Agent Reinforcement LearningJakob Foerster, Nantas Nardelli, Gregory Farquhar — 2017

Cited by

• Personalized Federated Reinforcement Learning for Multi-AAV Assisted Edge ComputingJ.-S. Chai, Zhe Wang, Chuan Ma — 2025
• Adaptive Edge Task Offloading via Parameterized Multi-Objective Reinforcement Learning With Hybrid Action SpaceHuimin Tong, Cheng Chen, Weihao Jiang — 2025

Related papers

• Parametrized Deep Q-Networks Learning: Reinforcement Learning with Discrete-Continuous Hybrid Action SpaceJiechao Xiong, Qing Wang, Zhuoran Yang — 2018
• Multi-Pass Q-Networks for Deep Reinforcement Learning with Parameterised Action SpacesCraig J. Bester, Steven D. James, George Konidaris — 2019
• HyAR: Addressing Discrete-Continuous Action Reinforcement Learning via Hybrid Action RepresentationBoyan Li, Hongyao Tang, Yan Zheng — 2021
• Using Deep Deterministic Policy Gradient (DDPG) to Train a Double-Jointed Arm to Reach Target Locations in the Unity ML-Agents Reacher EnvironmentOluwaseyi Awoga — 2021
• Deep Multi-Agent Reinforcement Learning with Discrete-Continuous Hybrid Action SpacesHaotian Fu, Hongyao Tang, Jianye Hao — 2019
• Encoding Topology Information for Deep Reinforcement Learning with Continuous Action SpaceQi Wang, Yue Gao, Wei Liu — 2019