no code implementations • 23 Jun 2021 • Jingda Wu, Zhiyu Huang, Chen Lv
Then, a novel uncertainty-aware model-based RL framework is developed based on the adaptive truncation approach, providing virtual interactions between the agent and environment model, and improving RL's training efficiency and performance.
no code implementations • 1 Jul 2022 • Jingda Wu, Wenhui Huang, Niels de Boer, Yanghui Mo, Xiangkun He, Chen Lv
Decisions made by human subjects in a driving simulator are treated as safe demonstrations, which are stored into the replay buffer and then utilized to enhance the training process of RL.
1 code implementation • 20 Jun 2022 • Wenhui Huang, Cong Zhang, Jingda Wu, Xiangkun He, Jie Zhang, Chen Lv
We theoretically prove that the policy improvement theorem holds for the preference-guided $\epsilon$-greedy policy and experimentally show that the inferred action preference distribution aligns with the landscape of corresponding Q-values.
1 code implementation • IEEE Transactions on Neural Networks and Learning Systems 2023 • Wenhui Huang, Cong Zhang, Jingda Wu, Xiangkun He, Jie Zhang, Chen Lv.
Stochastic exploration is the key to the success of the Deep Q-network (DQN) algorithm.
1 code implementation • 26 Sep 2021 • Jingda Wu, Zhiyu Huang, Wenhui Huang, Chen Lv
A novel prioritized experience replay mechanism that adapts to human guidance in the reinforcement learning process is proposed to boost the efficiency and performance of the reinforcement learning algorithm.
1 code implementation • 30 Jan 2022 • Qi Liu, Zirui Li, Xueyuan Li, Jingda Wu, Shihua Yuan
Several GRL approaches are summarized and implemented in the proposed framework.