James Mock

About

James Mock is a robotics researcher whose work sits at the intersection of deep reinforcement learning and legged locomotion. His primary focus is on developing and comparing state-of-the-art deep RL algorithms—specifically Proximal Policy Optimization (PPO), Twin Delayed Deep Deterministic Policy Gradient (TD3), and Soft Actor-Critic (SAC)—for generating stable, efficient walking gaits in quadruped robots. Mock’s most influential paper, “A Comparison of PPO, TD3 and SAC Reinforcement Algorithms for Quadruped Walking Gait Generation” (2023), has already garnered 33 citations, establishing a benchmark for algorithm selection in this domain. He extended this work in 2024 with a sim-to-real study, bridging the critical gap between virtual training environments and real-world robotic deployment. By systematically evaluating these algorithms under identical conditions, Mock provides practitioners with actionable guidance on which reinforcement learning approach yields the most robust and natural gait patterns. His contributions are particularly valuable for researchers seeking to replace classical robotic controllers with adaptive, learning-based alternatives, and his ongoing work continues to push the boundaries of autonomous locomotion in unstructured environments.

Research Focus

Key Achievements

Top Papers

1. 1
   A Comparison of PPO, TD3 and SAC Reinforcement Algorithms for Quadruped Walking Gait Generation

   33 citations · 2023
2. 2
   Sim-to-Real: A Performance Comparison of PPO, TD3, and SAC Reinforcement Learning Algorithms for Quadruped Walking Gait Generation

   5 citations · 2024

Key Collaborators

Contact & Links