15 citations · 50 across the 13 of their papers we have counts for
Showing 2026Show all
3 papers · 1 filter
cs.LG2026
Free Everywhere, Exact on Trees: PPO's Dropped Correction Buys Sample Efficiency Under Aggressive Reuse
Nima H. Siboni
Common policy improvement methods, including TRPO, PPO, and GRPO, estimate policy improvement under the behavioral policy's state-visitation distribution rather than the improved p…
cs.AI2026
On the "Causality" Step in Policy Gradient Derivations: A Pedagogical Reconciliation of Full Return and Reward-to-Go
Nima H. Siboni
In introductory presentations of policy gradients, one often derives the REINFORCE estimator using the full trajectory return and then states, by ``causality,'' that the full retur…
cs.AI2026
From Language Models to Control Policies: Search, Selection, and Verification
Nima H. Siboni, Seyedreza Kiamousavi, Vahid Rostami +1
Industrial process control demands policies that are interpretable and auditable, requirements that black-box neural policies struggle to meet. LLM-driven heuristic synthesis offer…