This work studies how policy improvement is composed through multi-step proximal policy improvement (MPI), which re-centers each proximal objective on the preceding policy, and identifies improvement composition as a design choice alongside regularization strength, with distinct effects from horizon subdivision and add...
Policy regularization in offline reinforcement learning balances policy improvement against reliance on uncertain value estimates. This balance can differ between selecting actions for execution and supplying actions for critic bootstrapping, yet methods such as TD3+BC couple these roles through a shared policy. We pro...
Energy-efficient control in dense wireless networks requires jointly optimizing user association, scheduling, and base station (BS) activation under finite energy budgets. Existing Lyapunov-based approaches enforce energy constraints only asymptotically. Under finite-horizon operation, the myopic per-slot drift-plus-pe...
Wonhyeok Ko, Yeonseo Jeong, Sungweon Hong et al.· IEEE Internet of Things Jour...· 1 citation
This work proposes a lightweight and information-theoretically secure aggregation framework that securely computes the majority vote (MV) polynomial through single-round secure multiplication, ensuring end-to-end information-theoretic security under the honest-majority assumption while revealing only the final aggregat...
Robust reinforcement learning (RRL) aims to develop a robust policy that maintains stable performance across diverse environments characterized by an uncertainty set. This set consists of perturbed environments derived from a nominal (training) environment that generates samples, thereby capturing potential discrepanci...
Ukjo Hwang, Songnam Hong· IEEE Transactions on Neural...· 0 citations
Offline reinforcement learning (RL) must reconcile two competing requirements: policy updates should stay near dataset-supported actions to keep value estimates reliable, yet meaningful gains often require moving beyond the behavior distribution. We develop a geometric view of offline actor updates by modeling policies...
The proposed PathBridger is a hierarchical offline GCRL method that explicitly connects subgoal selection to short-horizon execution, and constructs a state-space bridge toward the selected intermediate endpoint and decodes it into a short executable action chunk using an inverse dynamics model.
Simulations show that HeLyMARL is the only method that sustains the throughput-fairness balance together with uninterrupted service throughout the horizon, outperforming conventional MARL, Lyapunov-based, and constrained MARL benchmarks without premature budget exhaustion.
Yeonseo Jeong, Wonhyeok Ko, Sungweon Hong et al.· 0 citations
This work proposes a lightweight and information-theoretically secure aggregation framework that securely computes the majority vote (MV) polynomial through single-round secure multiplication, ensuring end-to-end information-theoretic security under the honest-majority assumption while revealing only the final aggregat...
