SJSiyang Jiang

Siyang Jiang

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Siyang Jiang has a total of 7 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
  • Wei Ding

    National Taiwan University

    2 shared publications
  • Haibin Wu

    Graduate Institute of Networking and Multimedia Graduate Institute of Electrical Engineering Department of Computer Science Graduate Institute of Communication Engineering Department of Computer Science National Taiwan University Taipei National Taiwan University Taipei National Taiwan University Taipei National Taiwan University Taipei National Taiwan University Taipei

    1 shared publication
  • Jian Hu

    Graduate Institute of Networking and Multimedia Graduate Institute of Electrical Engineering Department of Computer Science Graduate Institute of Communication Engineering Department of Computer Science National Taiwan University Taipei National Taiwan University Taipei National Taiwan University Taipei National Taiwan University Taipei National Taiwan University Taipei

    1 shared publication
  • Seth Austin Harding

    Graduate Institute of Networking and Multimedia Graduate Institute of Electrical Engineering Department of Computer Science Graduate Institute of Communication Engineering Department of Computer Science National Taiwan University Taipei National Taiwan University Taipei National Taiwan University Taipei National Taiwan University Taipei National Taiwan University Taipei

    1 shared publication

Latest Publications

  • Open Access

    Incremental Reinforcement Learning with Dual-Adaptive ε-Greedy Exploration

    by Wei Ding, Siyang Jiang, Hsi-Wen Chen, Ming-Syan Chen

    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.


  • Open Access

    Rethinking the Implementation Tricks and Monotonicity Constraint in Cooperative Multi-Agent Reinforcement Learning

    by Jian Hu, Siyang Jiang, Seth Austin Harding, Haibin Wu, Shih-Wei Liao

    Many complex multi-agent systems such as robot swarms control and autonomous vehicle coordination can be modeled as Multi-Agent Reinforcement Learning (MARL) tasks. QMIX, a widely popular MARL algorithm, has been used as a baseline for the benchmark environments, e.g., Starcraft Multi-Agent Challenge (SMAC), Difficulty-Enhanced Predator-Prey (DEPP). Recent variants of QMIX target relaxing the monotonicity constraint of QMIX, allowing for performance improvement in SMAC. In this paper, we investigate the code-level optimizations of these variants and the monotonicity constraint. (1) We find that such improvements of the variants are significantly affected by various code-level optimizations. (2) The experiment results show that QMIX with normalized optimizations outperforms other works in SMAC; (3) beyond the common wisdom from these works, the monotonicity constraint can improve sample efficiency in SMAC and DEPP. We also discuss why monotonicity constraints work well in purely cooperative tasks with a theoretical analysis. We open-source the code at \url{https://github.com/hijkzzz/pymarl2}.