This paper introduces a curriculum‑driven proximal policy optimization (PPO) framework for three‑dimensional rocket landing in a stochastic environment that includes altitude‑dependent aerodynamic drag, wind shear, temporally correlated turbulence, discrete gusts, uncertain propulsion and aerodynamic parameters, thrust‑vector misalignment, engine lag, actuator‑gain variation, noisy observations, and command latency. Learning is organized into three stages: far‑range approach, soft descent, and integrated landing. To support cross‑stage learning, the method employs policy transfer, critic warm‑up after reward changes, rehearsal of earlier tasks, and progressive expansion of weather severity.
Across 100,000 evaluation episodes the policy achieves 96,656 successful landings, a success rate of 96.656\% with a 95\% Wilson confidence interval of 96.543%–96.766%. Success drops from 98.84\% under zero‑disturbance conditions to 88.07\% in the highest weather‑severity band. Successful touchdowns exhibit small miss distances and low residual horizontal and vertical velocities. An exploratory logistic‑regression analysis identifies mean wind speed as the strongest correlate of success, followed by initial distance, initial altitude, initial vertical velocity, and wind‑shear exponent. The results quantify both the effectiveness of the learned policy over the evaluated disturbance distribution and the degradation under severe compound atmospheric conditions.
Review