Planning Immediate Landmarks of Targets for Model-Free Skill Transfer across Agents
This addresses sample inefficiency for developers in robotics and RL applications, though it is incremental as it builds on existing goal-conditioned and transfer learning methods.
The paper tackles the problem of inefficient retraining in reinforcement learning when agents have different state/action spaces, proposing PILoT to transfer high-level goal-transition knowledge across agents, achieving few-shot and zero-shot transfer in tasks like navigation and robotics.
In reinforcement learning applications like robotics, agents usually need to deal with various input/output features when specified with different state/action spaces by their developers or physical restrictions. This indicates unnecessary re-training from scratch and considerable sample inefficiency, especially when agents follow similar solution steps to achieve tasks. In this paper, we aim to transfer similar high-level goal-transition knowledge to alleviate the challenge. Specifically, we propose PILoT, i.e., Planning Immediate Landmarks of Targets. PILoT utilizes the universal decoupled policy optimization to learn a goal-conditioned state planner; then, distills a goal-planner to plan immediate landmarks in a model-free style that can be shared among different agents. In our experiments, we show the power of PILoT on various transferring challenges, including few-shot transferring across action spaces and dynamics, from low-dimensional vector states to image inputs, from simple robot to complicated morphology; and we also illustrate a zero-shot transfer solution from a simple 2D navigation task to the harder Ant-Maze task.