Learning Emergent Gaits with Decentralized Phase Oscillators: on the role of Observations, Rewards, and Feedback

1 code implementation • 13 Feb 2024 • Jenny Zhang, Steve Heim, Se Hwan Jeon, Sangbae Kim

We present a minimal phase oscillator model for learning quadrupedal locomotion.

Benchmarking Potential Based Rewards for Learning Humanoid Locomotion

1 code implementation • 19 Jul 2023 • Se Hwan Jeon, Steve Heim, Charles Khazoom, Sangbae Kim

Although several studies have explored the use of potential based reward shaping to accelerate learning convergence, most have been limited to grid-worlds and low-dimensional systems, and RL in robotics has predominantly relied on standard forms of reward shaping.

Benchmarking Reinforcement Learning (RL)