Published:
We propose a parameter-dependent conditional generative adversarial network for predicting multi-phase flows. By conditioning the model on specific fuel parameters and input images, we accurately synthesize the resulting fuel morphology.
Published:
We improved exsting numerical solver using Richardson Extrapolation for Wave equations such as Helmholtz equation and partial differential equations.
Published in (AAAI-24) The Association for the Advancement of Artificial Intelligence, 2024
We propose a policy optimization framework that provides adaptable safety guarantees on unseen tasks by viewing constrained reinforcement learning through the lens of meta-learning.
Recommended citation: Cho, Minjae, and Chuangchuang Sun. "Constrained meta-reinforcement learning for adaptable safety guarantee with differentiable convex programming." Proceedings of the AAAI Conference on Artificial Intelligence. Vol. 38. No. 19. 2024.
Download Paper
Published in arXiv preprint arXiv:2412.11930, 2024
We propose a macro-action discovery method and use it in a hierarchical algorithm for solving complex meta-RL problems.
Recommended citation: Cho, Minjae, and Chuangchuang Sun. "Hierarchical meta-reinforcement learning via automated macro-action discovery." arXiv preprint arXiv:2412.11930 (2024).
Download Paper
Published in arXiv preprint arXiv:2506.15700, 2025
We propose a contraction actor-critic (CAC) algorithm for endowing a stability guarantee to the RL-trained policies for high-dimensional and nonlinear path-tracking problems.
Recommended citation: Cho, Minjae, Hiroyasu Tsukamoto, and Huy Trong Tran. "Contraction Actor-Critic: Contraction Metric-Guided Reinforcement Learning for Robust Path Tracking." arXiv preprint arXiv:2506.15700 (2025).
Download Paper
Published in Mathematics: Statistics and Operational Research, 2025
We propose to learn transition dynamics and reward function using causal normalizing flow model for out-of-distribution adaptation of a policy.
Recommended citation: Cho, M., & Sun, C. (2025). "Out of Distribution Adaptation in Offline RL via Causal Normalizing Flows." Mathematics, 13(23), 3835.
Download Paper
Published in arXiv preprint arXiv:2601.21391, 2026
We propose Intrinsic Reward Policy Optimization (IRPO), a novel framework leveraging a surrogate policy gradient to overcome credit assignment and sample inefficiency in sparse-reward environments.
Recommended citation: Cho, M., & Tran, H. T. (2026). "Intrinsic Reward Policy Optimization for Sparse-Reward Environments." arXiv preprint arXiv:2601.21391.
Download Paper
Published in (AIAA-26) AIAA AVIATION Forum 2026, 2026
We propose to use K-Mean clustering algorithm to measure the sparsity of each data point and use those measures to overestimate the probable safety violation for safe deployment of a policy.
Recommended citation: Cho, Minjae, and Chuangchuang Sun. "Sparsity-based Safety Conservatism for Constrained Offline Reinforcement Learning." arXiv preprint arXiv:2407.13006 (2024).
Download Paper
Published:
This is a description of your talk, which is a markdown file that can be all markdown-ified like any other post. Yay markdown!
Published:
This is a description of your tutorial, note the different field in type. This is a markdown files that can be all markdown-ified like any other post. Yay markdown!
Published:
This is a description of your talk, which is a markdown files that can be all markdown-ified like any other post. Yay markdown!
Published:
This is a description of your conference proceedings talk, note the different field in type. You can put anything in this field.
TA, , 2023
Assisted in instruction for electromagnetism, optics, and modern physics. Managed supplemental intruction sessions for students.
TA, Department of Aerospace Engineering, 2025
Assisted in instruction for rigid body dynamics, orbital mechanics, and Lagrangian mechanics.
TA, Department of Aerospace Engineering, 2025
Assisted in the instruction of classical control theory, state-space analysis, and stability for aerospace vehicles.
TA, Department of Aerospace Engineering, 2026
Assisted in instruction for rigid body dynamics, orbital mechanics, and Lagrangian mechanics.