Test-driven Reinforcement Learning In Continuous Control

Abstract

Reinforcement learning (RL) has been recognized as a powerful tool for robot control tasks. RL typically employs reward functions to define task objectives and guide agent learning. However, since the reward function serves the dual purpose of defining the optimal goal and guiding learning, it is challenging to design the reward function manually, which often results in a suboptimal task representation. To tackle the reward design challenge in RL, inspired by the satisficing theory, we propose a Test-driven Reinforcement Learning (TdRL) framework. In the TdRL framework, multiple test functions are used to represent the task objective rather than a single reward function. Test functions can be categorized as pass-fail tests and indicative tests, each dedicated to defining the optimal objective and guiding the learning process, respectively, thereby making defining tasks easier. Building upon such a task definition, we first prove that if a trajectory return function assigns higher retur

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyyu2025test

Related papers

• REBEL: Reward Regularization-based Approach For Robotic Reinforcement Learning From Human Feedback (2023)0.00
• Adaptive Reward Design For Reinforcement Learning (2024)0.00
• TGRL: An Algorithm For Teacher Guided Reinforcement Learning (2023)0.00
• Reward Design For Reinforcement Learning Agents (2025)0.00
• DQN-TAMER: Human-in-the-loop Reinforcement Learning With Intractable Feedback (2018)0.00
• Provably Feedback-efficient Reinforcement Learning Via Active Reward Learning (2023)0.00
• Knowledge Transfer In Multi-task Deep Reinforcement Learning For Continuous Control (2020)0.00
• Control-optimized Deep Reinforcement Learning For Artificially Intelligent Autonomous Systems (2025)0.00