Growing Action Spaces
This addresses the challenge of learning in complex environments with large action spaces for reinforcement learning practitioners, though it appears incremental as it builds on existing curriculum and off-policy methods.
The paper tackles the problem of inefficient exploration in reinforcement learning tasks with large combinatorial action spaces by using a curriculum of progressively growing action spaces to accelerate learning, showing efficacy in control tasks and StarCraft micromanagement tasks.
In complex tasks, such as those with large combinatorial action spaces, random exploration may be too inefficient to achieve meaningful learning progress. In this work, we use a curriculum of progressively growing action spaces to accelerate learning. We assume the environment is out of our control, but that the agent may set an internal curriculum by initially restricting its action space. Our approach uses off-policy reinforcement learning to estimate optimal value functions for multiple action spaces simultaneously and efficiently transfers data, value estimates, and state representations from restricted action spaces to the full task. We show the efficacy of our approach in proof-of-concept control tasks and on challenging large-scale StarCraft micromanagement tasks with large, multi-agent action spaces.