Wei Ding
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Wei Ding has a total of 3 co-authors. Here are the top co-authors by number of shared publications:
- Hsi-Wen Chen
National Taiwan University
2 shared publications - Ming-Syan Chen
National Taiwan University
2 shared publications - Siyang Jiang
National Taiwan University
2 shared publications
Latest Publications
- Open Access
- 26 June 2023
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 37 (6) , 7387-7395
Incremental Reinforcement Learning with Dual-Adaptive ε-Greedy Exploration
Reinforcement learning (RL) has achieved impressive performance in various domains. However, most RL frameworks oversimplify the problem by assuming a fixed-yet-known environment and often have difficulty being generalized to real-world scenarios. In this paper, we address a new challenge with a more realistic setting, Incremental Reinforcement Learning, where the search space of the Markov Decision Process continually expands. While previous methods usually suffer from the lack of efficiency in exploring the unseen transitions, especially with increasing search space, we present a new exploration framework named Dual-Adaptive ϵ-greedy Exploration (DAE) to address the challenge of Incremental RL. Specifically, DAE employs a Meta Policy and an Explorer to avoid redundant computation on those sufficiently learned samples. Furthermore, we release a testbed based on a synthetic environment and the Atari benchmark to validate the effectiveness of any exploration algorithms under Incremental RL. Experimental results demonstrate that the proposed framework can efficiently learn the unseen transitions in new environments, leading to notable performance improvement, i.e., an average of more than 80%, over eight baselines examined.
- 26 June 2023
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 37 (6) , 7387-7395
Open AccessIncremental Reinforcement Learning with Dual-Adaptive ε-Greedy Exploration
Reinforcement learning (RL) has achieved impressive performance in various domains. However, most RL frameworks oversimplify the problem by assuming a fixed-yet-known environment and often have difficulty being generalized to real-world scenarios. In this paper, we address a new challenge with a more realistic setting, Incremental Reinforcement Learning, where the search space of the Markov Decision Process continually expands. While previous methods usually suffer from the lack of efficiency in exploring the unseen transitions, especially with increasing search space, we present a new exploration framework named Dual-Adaptive ϵ-greedy Exploration (DAE) to address the challenge of Incremental RL. Specifically, DAE employs a Meta Policy and an Explorer to avoid redundant computation on those sufficiently learned samples. Furthermore, we release a testbed based on a synthetic environment and the Atari benchmark to validate the effectiveness of any exploration algorithms under Incremental RL. Experimental results demonstrate that the proposed framework can efficiently learn the unseen transitions in new environments, leading to notable performance improvement, i.e., an average of more than 80%, over eight baselines examined.
- 10 May 2022
- Published by Springer Nature
- p. 3-15
PGADA: Perturbation-Guided Adversarial Alignment for Few-Shot Learning Under the Support-Query Shift
- 10 May 2022
- Published by Springer Nature
- p. 3-15
PGADA: Perturbation-Guided Adversarial Alignment for Few-Shot Learning Under the Support-Query Shift