4 papers
Offline Reinforcement Learning with Universal Horizon Models
Hojun Chung, Junseo Lee, Songhwai Oh
Model-based reinforcement learning (RL) offers a compelling approach to offline RL by enabling value learning on imagined on-policy trajectories. However, it often suffers from com…
Adversarial Environment Design via Regret-Guided Diffusion Models
Hojun Chung, Junseo Lee, Minsoo Kim +2
Training agents that are robust to environmental changes remains a significant challenge in deep reinforcement learning (RL). Unsupervised environment design (UED) has recently eme…
Spectral-Risk Safe Reinforcement Learning with Convergence Guarantees
Dohyeong Kim, Taehyun Cho, Seungyub Han +3
The field of risk-constrained reinforcement learning (RCRL) has been developed to effectively reduce the likelihood of worst-case scenarios by explicitly handling risk-measure-base…
Towards Defensive Autonomous Driving: Collecting and Probing Driving Demonstrations of Mixed Qualities
Jeongwoo Oh, Gunmin Lee, Jeongeun Park +8
Designing or learning an autonomous driving policy is undoubtedly a challenging task as the policy has to maintain its safety in all corner cases. In order to secure safety in auto…