Publications

International Journal

• Dohyeong Kim and Songhwai Oh, “Efficient Off-Policy Safe Reinforcement Learning Using Trust Region Conditional Value at Risk,” IEEE Robotics and Automation Letters, vol. 7, no. 3, pp. 7644-7651, Jul. 2022. arXiv Video Code

• Dohyeong Kim and Songhwai Oh, “TRC: Trust Region Conditional Value at Risk for Safe Reinforcement Learning,” IEEE Robotics and Automation Letters, vol. 7, no. 2, pp. 2621-2628, Apr. 2022. arXiv Video Code

International Conference

• Dohyeong Kim, Taehyun Cho, Seungyub Han, Hojun Chung, Kyungjae Lee, and Songhwai Oh, “Spectral-Risk Safe Reinforcement Learning with Convergence Guarantees,” in Proc. of Neural Information Processing Systems (NeurIPS), Dec. 2024. arXiv

• Hojun Chung, Junseo Lee, Minsoo Kim, Dohyeong Kim, and Songhwai Oh, “Adversarial Environment Design via Regret-Guided Diffusion Models,” in Proc. of Neural Information Processing Systems (NeurIPS), Dec. 2024. (Spotlight 🌟)

• Dohyeong Kim, Kyungjae Lee, and Songhwai Oh, “Trust Region-Based Safe Distributional Reinforcement Learning for Multiple Constraints,” in Proc. of Neural Information Processing Systems (NeurIPS), Dec. 2023. Project Page Video Code

• Junseo Lee, Jaeseok Heo, Dohyeong Kim, Gunmin Lee, and Songhwai Oh, “Dual Variable Actor-Critic for Adaptive Safe Reinforcement Learning,” in Proc. of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Oct. 2023. Video

• Hogun Kee, Minjae Kang, Dohyeong Kim, Jaegoo Choy, and Songhwai Oh, “SDF-Based Graph Convolutional Q-Networks for Rearrangement of Multiple Objects,” in Proc of the IEEE International Conference on Robotics and Automation (ICRA), May 2023. Video

• Gunmin Lee, Wooseok Oh, Jeongwoo Oh, Seungyoun Shin, Dohyeong Kim, Jaeyeon Jeong, Sungjoon Choi, and Songhwai Oh “Semi-Supervised Imitation Learning with Mixed Qualities of Demonstrations for Autonomous Driving,” in Proc. of the International Conference on Control, Automation and Systems (ICCAS), Nov. 2022.  arXiv

• Dohyeong Kim*, Jaeseok Heo*, and Songhwai Oh, “SafeTAC: Safe Tsallis Actor-Critic Reinforcement Learning for Safer Exploration,” in Proc. of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Oct. 2022. Paper Video

• Dohyeong Kim, Yunho Kim, Kyungjae Lee, and Songhwai Oh, “Safety Guided Policy Optimization,” in Proc. of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Oct. 2022. Paper Video

• Dohyeong Kim and Songhwai Oh, “Efficient Off-Policy Safe Reinforcement Learning Using Trust Region Conditional Value at Risk,” IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Oct. 2022. (RA-L option) arXiv Video Code

• Dohyeong Kim and Songhwai Oh, “TRC: Trust Region Conditional Value at Risk for Safe Reinforcement Learning,” IEEE International Conference on Robotics and Automation (ICRA), May 2022. (RA-L option) arXiv Video Code

• Hogun Kee, Dohyeong Kim, and Songhwai Oh, “Decomposed Q-Learning for Non-Prehensile Rearrangement Problem,” in Proc. of the International Conference on Control, Automation and Systems (ICCAS), Oct. 2021.

• Timothy Ha, Gunmin Lee, Dohyeong Kim, and Songhwai Oh, “Road Graphical Neural Networks for Autonomous Roundabout Driving,” in Proc. of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Sep. 2021. Paper Video

• Gunmin Lee*, Dohyeong Kim*, Wooseok Oh, Kyungjae Lee, and Songhwai Oh, “MixGAIL: Autonomous Driving Using Demonstrations with Mixed Qualities,” in Proc. of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Oct. 2020. Paper Video