Novel Policy Seeking with Constrained Optimization

v1v2v3 (latest)

Novel Policy Seeking with Constrained Optimization

21 May 2020

ArXiv (abs)PDF HTML

Papers citing "Novel Policy Seeking with Constrained Optimization"

7 / 7 papers shown

Title
$β$ -DQN: Improving Deep Q-Learning By Evolving the BehaviorAdaptive Agents and Multi-Agent Systems (AAMAS), 2025 Hongming Zhang Fengshuo Bai Chenjun Xiao Chao Gao Bo Xu Martin Müller OffRL 168 4 0 01 Jan 2025
Iteratively Learn Diverse Strategies with State Distance InformationNeural Information Processing Systems (NeurIPS), 2023 Wei Fu Weihua Du Jingwei Li Sunli Chen Jingzhao Zhang Yi Wu 182 5 0 23 Oct 2023
Keep Various Trajectories: Promoting Exploration of Ensemble Policies in Continuous ControlNeural Information Processing Systems (NeurIPS), 2023 Chao Li Chen Gong Qiang He Xinwen Hou 119 2 0 17 Oct 2023
Reinforcement Learning in the Era of LLMs: What is Essential? What is needed? An RL Perspective on RLHF, Prompting, and Beyond Hao Sun OffRL 117 25 0 09 Oct 2023
Diversifying AI: Towards Creative Chess with AlphaZero Tom Zahavy Vivek Veeriah Shaobo Hou Kevin Waugh Matthew Lai Edouard Leurent Nenad Tomašev Lisa Schut Demis Hassabis Satinder Singh 187 20 0 17 Aug 2023
Continuously Discovering Novel Strategies via Reward-Switching Policy OptimizationInternational Conference on Learning Representations (ICLR), 2022 Zihan Zhou Wei Fu Bingliang Zhang Yi Wu 160 34 0 04 Apr 2022
Discovering Diverse Athletic Jumping StrategiesACM Transactions on Graphics (TOG), 2021 Zhiqi Yin Zeshi Yang M. van de Panne KangKang Yin 156 47 0 02 May 2021