Investigating Reinforcement Learning Agents for Continuous State Space Environments

Given an environment with continuous state spaces and discrete actions, we investigate using a Double Deep Q-learning Reinforcement Agent to find optimal policies using the LunarLander-v2 OpenAI gym environment.

cs.AI Computer Science

View graph Source

Paper

References (4)

01Deep Reinforcement Learning with Double Q-LearningH. V. Hasselt, A. Guez, David Silver2015 · AAAI Conference on Artificial Intelligence · 9.3k citations In Library

02Human-level control through deep reinforcement learningVolodymyr Mnih, K. Kavukcuoglu, David Silver et al.2015 · Nature · 33k citations

03Reinforcement Learning in Continuous State SpacesH. Kamaya, Kazuyuki Kitayama, Atsuko Fujimura et al.2006 · 4 citations

04Hado van Hasselt -Double Q-learning2010 · Advances in Neural Information Processing Systems

Solving The Lunar Lander Problem under Uncertainty using Reinforcement LearningSoham Gadgil, Yunfeng Xin, Chengzhe Xu2020 In Library

Solving The Lunar Lander Problem under Uncertainty using Reinforcement LearningSoham Gadgil, Yunfeng Xin, Chengzhe Xu2020 · arXiv (Cornell University) · 15 citations In Library

Autonomous Agent Learning for Navigation in continuous Environments: Deep Reinforcement Learning ApproachIna'am Rabah, Maha A. Al-Bayati, Farah Q. Al-Khalidi2025 · Academic Science Journal In Library

Learning Environment Models with Continuous Stochastic DynamicsMartin Tappler, Edi Muškardin, Bernhard K. Aichernig et al.2023 · arXiv (Cornell University) In Library

Safe Deep Reinforcement Learning for Multi-Agent Systems with Continuous Action SpacesZiyad Sheebaelhamd, Konstantinos Zisis, Athina Nisioti et al.2021 · arXiv (Cornell University) · 22 citations In Library

Online Deep Reinforcement Learning for Autonomous UAV Navigation and Exploration of Outdoor EnvironmentsBruna G. Maciel-Pearson, Letizia Marchegiani, S. Akçay et al.2019 · arXiv.org · 37 citations In Library

Learning Agents With Prioritization and Parameter Noise in Continuous State and Action SpaceRajesh Mangannavar, G. Srinivasaraghavan2019 · International Symposium on Neural Networks · 2 citations In Library

Using Deep Deterministic Policy Gradient (DDPG) to Train a Double-Jointed Arm to Reach Target Locations in the Unity ML-Agents Reacher EnvironmentAwoga Cpa, Prm, Oluwaseyi2021 · Social Science Research Network · 0 citations In Library

Deep Multi-Agent Reinforcement Learning with Discrete-Continuous Hybrid Action SpacesHaotian Fu, Hongyao Tang, Jianye Hao et al.2019 · International Joint Conference on Artificial Intelligence · 84 citations In Library

Patents near this paper

APPARATUS FOR Q-LEARNING FOR CONTINUOUS ACTIONS WITH CROSS-ENTROPY GUIDED POLICIES AND METHOD THEREOFUS 11,710,301 · SAMSUNG ELECTRONICS CO., LTD. · 2023 WEAKLY SUPERVISED REINFORCEMENT LEARNINGUS 11,809,977 · NEC LABORATORIES EUROPE GMBH · 2023 DISTRIBUTIONAL REINFORCEMENT LEARNING FOR CONTINUOUS CONTROL TASKSUS 11,663,475 · DEEPMIND TECHNOLOGIES LIMITED · 2023 DISTRIBUTIONAL REINFORCEMENT LEARNING FOR CONTINUOUS CONTROL TASKSUS 11,481,629 · DEEPMIND TECHNOLOGIES LIMITED · 2022 ENVIRONMENT NAVIGATION USING REINFORCEMENT LEARNINGUS 11,074,481 · DEEPMIND TECHNOLOGIES LIMITED · 2021

Source of record

arXiv

Investigating Reinforcement Learning Agents for Continuous State Space Environments

Paper

References (4)

Similar papers

Patents near this paper

Welcome.

Patents near this paper