paper-with-me

Papers

STRIDE: Automating Reward Design, Deep Reinforcement Learning Training and Feedback Optimization in Humanoid Robotics Locomotion

2025-02-07 · Zhenwei Wu, Jinxiong Lu, Yuxiao Chen, Yunxin Liu, Yueting Zhuang, Luhui Hu

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.

📄 PDF Abstract BibTeX arXiv:2502.04692

Code (0)

등록된 구현이 없습니다.

Tasks

Deep Reinforcement Learning

Similar Papers 제목 키워드 기반

STRIDE: Strategic Trajectory Reasoning via Discriminative Estimation for Verifiable Reinforcement Learning

2026-06-14 · Qinjian Zhao, Zhihao Dou, Dinggen Zhang, Xiangyu Li 외 arxiv

Reinforcement Learning with Verifiable Rewards (RLVR) has become an effective post-training paradigm for improving the reasoning abilities of large language models. However, existing RLVR methods typically rely on final-…

Reinforcement Learning

From Intent to Execution: Multimodal Chain-of-Thought Reinforcement Learning for Precise CAD Code Generation

2025-08-13 · Ke Niu, Haiyang Yu, Zhuofan Chen, Mengyang Zhao 외 arxiv

Computer-Aided Design (CAD) plays a vital role in engineering and manufacturing, yet current CAD workflows require extensive domain expertise and manual modeling effort. Recent advances in large language models (LLMs) ha…

Reinforcement LearningLogical ReasoningCode Generation

StriderNET: A Graph Reinforcement Learning Approach to Optimize Atomic Structures on Rough Energy Landscapes

2023-01-29 · Vaibhav Bihani, Sahil Manchanda, Srikanth Sastry, Sayan Ranu 외

Optimization of atomic structures presents a challenging problem, due to their highly rough and non-convex energy landscape, with wide applications in the fields of drug design, materials discovery, and mechanics. Here, …

Drug Design

STRIDE: Learnable Stepwise Language Feedback for LLM Reasoning

2026-05-13 · Junjie Zhang, Guozheng Ma, Shunyu Liu, Zetian Hu 외 arxiv

Recent advances in Reinforcement Learning (RL) have underscored its potential for incentivizing reasoning capabilities of Large Language Models (LLMs). However, existing step-level efforts suffer from costly annotations …

Reinforcement Learning

PRO-CUA: Process-Reward Optimization for Computer Use Agents

2026-05-27 · Yifei He, Rui Yang, Hao Bai, Tong Zhang 외 arxiv

Computer use agents (CUAs) have shown strong potential for automating complex digital workflows, yet their training remains constrained by costly live environment interaction and limited high-quality supervision. Existin…

Reinforcement Learning