An LLM-driven agent with built-in seed-noise audits develops control policies for two aerospace problems that outperform undirected search and pass verification checks.
Title resolution pending
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
years
2026 5verdicts
UNVERDICTED 5representative citing papers
A distribution-agnostic robust trajectory optimization framework uses chance-constrained reinforcement learning with rollout-based quantiles to enforce probabilistic feasibility on nominal trajectories via affine corrections.
Neural surrogates trained with scaling laws and self-similar transformations accurately approximate low-thrust trajectory costs and reachability while generalizing across orbital parameters.
Empirical comparison finds Mamba with PPO superior to LSTM/GRU and SAC variants for meta-RL tuning of ICCBF class-K functions in cooperative and adversarial spacecraft RPO simulations.
Analyzes likelihood-constrained adversarial observation shifts and their effects on latent states and policies in linear probabilistic SSMs used for RL.
citing papers explorer
-
Distribution-Agnostic Robust Trajectory Optimization via Chance-Constrained Reinforcement Learning
A distribution-agnostic robust trajectory optimization framework uses chance-constrained reinforcement learning with rollout-based quantiles to enforce probabilistic feasibility on nominal trajectories via affine corrections.