A three-stage curriculum RL policy for end-to-end quadrotor stabilization outperforms single-stage training in sample efficiency and robustness in simulation.
Trust Region Policy Optimization,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Curriculum-based Sample Efficient Reinforcement Learning for Robust Stabilization of a Quadrotor
A three-stage curriculum RL policy for end-to-end quadrotor stabilization outperforms single-stage training in sample efficiency and robustness in simulation.