Growing Action Spaces
arXiv:1906.12266
Abstract
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.
References in corpus (7)
- An Overview of Multi-Task Learning in Deep Neural Networks
- Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm
- StarCraft II: A New Challenge for Reinforcement Learning
- Rainbow: Combining Improvements in Deep Reinforcement Learning
- Competitive Coevolution through Evolutionary Complexification
- Episodic Exploration for Deep Deterministic Policies: An Application to StarCraft Micromanagement Tasks
- TorchCraft: a Library for Machine Learning Research on Real-Time Strategy Games