mlsanityData to 7 Oct 2026

Deriving Rewards for Reinforcement Learning from Symbolic Behaviour Descriptions of Bipedal Walking

arXiv 2312.10328 ↗First posted 16 Dec 2023cs.RO cs.LG cs.LOcited by 0

Not on the map. Why?

Abstract (arXiv)

Generating physical movement behaviours from their symbolic description is a long-standing challenge in artificial intelligence (AI) and robotics, requiring insights into numerical optimization methods as well as into formalizations from symbolic AI and reasoning. In this paper, a novel approach to finding a reward function from a symbolic description is proposed. The intended system behaviour is modelled as a hybrid automaton, which reduces the system state space to allow more efficient reinforcement learning. The approach is applied to bipedal walking, by modelling the walking robot as a hybrid automaton over state space orthants, and used with the compass walker to derive a reward that incentivizes following the hybrid automaton cycle. As a result, training times of reinforcement learning controllers are reduced while final walking speed is increased. The approach can serve as a blueprint how to generate reward functions from symbolic AI and reasoning.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 11 of its 25 references that are in the map. First posted on arXiv 16 Dec 2023.

Builds on

11 of 25 references.

References · 11

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2020Learning Quadrupedal Locomotion over Challenging Terraincited by 494
  3. 2021Learning to Walk in Minutes Using Massively Parallel Deep Reinforcement Learningcited by 395
  4. 2018A Survey of Inverse Reinforcement Learning: Challenges, Methods and Progresscited by 294
  5. 2021Reinforcement Learning for Robust Parameterized Locomotion Control of Bipedal Robotscited by 95
  6. 2022A Walk in the Park: Learning to Walk in 20 Minutes With Model-Free Reinforcement Learningcited by 76
  7. 2020Sim-to-Real Learning of All Common Bipedal Gaits via Periodic Reward Compositioncited by 71
  8. 2021Minimizing Energy Consumption Leads to the Emergence of Gaits in Legged Robotscited by 67
  9. 2018Learning Symmetric and Low-energy Locomotioncited by 53
  10. 2020Learning Spring Mass Locomotion: Guiding Policies with a Reduced-Order Modelcited by 8
  11. 2021Design, analysis and control of the series-parallel hybrid RH5 humanoid robotcited by 1

Built on by

Not cited yet.