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

December 16, 2023 · Entered Twilight · 🏛 IEEE Conference on Decision and Control

"No code URL or promise found in abstract"
"Derived repo from GitHub Pages (backfill)"

Evidence collected by the PWNC Scanner

Repo contents: LICENSE, README.md, controller, docs, landing-page, orthants, parameters, path_handling, plant, requirements.txt, rl_environments, rl_training, scripts, simulator, visualization

Authors Daniel Harnack, Christoph Lüth, Lukas Gross, Shivesh Kumar, Frank Kirchner arXiv ID 2312.10328 Category cs.RO: Robotics Cross-listed cs.LG, cs.LO Citations 1 Venue IEEE Conference on Decision and Control Repository https://github.com/dfki-ric-underactuated-lab/orthant_rewards_biped_rl Last Checked 3 months ago

Abstract

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.