STRIDE: Automating Reward Design, Deep Reinforcement Learning Training and Feedback Optimization in Humanoid Robotics Locomotion
This addresses the bottleneck of manual reward design for researchers and engineers in humanoid robotics, though it is incremental as it builds on existing frameworks like EUREKA.
The paper tackles the challenge of designing effective reward functions for deep reinforcement learning in humanoid robotics by introducing STRIDE, a framework that automates reward design, training, and feedback optimization, resulting in a 250% average improvement in efficiency and task performance over the state-of-the-art method EUREKA.
Humanoid robotics presents significant challenges in artificial intelligence, requiring precise coordination and control of high-degree-of-freedom systems. Designing effective reward functions for deep reinforcement learning (DRL) in this domain remains a critical bottleneck, demanding extensive manual effort, domain expertise, and iterative refinement. To overcome these challenges, we introduce STRIDE, a novel framework built on agentic engineering to automate reward design, DRL training, and feedback optimization for humanoid robot locomotion tasks. By combining the structured principles of agentic engineering with large language models (LLMs) for code-writing, zero-shot generation, and in-context optimization, STRIDE generates, evaluates, and iteratively refines reward functions without relying on task-specific prompts or templates. Across diverse environments featuring humanoid robot morphologies, STRIDE outperforms the state-of-the-art reward design framework EUREKA, achieving an average improvement of round 250% in efficiency and task performance. Using STRIDE-generated rewards, simulated humanoid robots achieve sprint-level locomotion across complex terrains, highlighting its ability to advance DRL workflows and humanoid robotics research.