The Intentional Unintentional Agent: Learning to Solve Many Continuous Control Tasks Simultaneously
This addresses the core AI goal of building flexible robot manipulators with diverse behaviors, though it appears incremental as it extends DDPG for multi-task learning.
The paper tackles the problem of learning to solve multiple continuous control tasks simultaneously by introducing the Intentional Unintentional (IU) agent, which shows faster learning and success in cases where single-task methods fail, as demonstrated in a MuJoCo-based playroom environment.
This paper introduces the Intentional Unintentional (IU) agent. This agent endows the deep deterministic policy gradients (DDPG) agent for continuous control with the ability to solve several tasks simultaneously. Learning to solve many tasks simultaneously has been a long-standing, core goal of artificial intelligence, inspired by infant development and motivated by the desire to build flexible robot manipulators capable of many diverse behaviours. We show that the IU agent not only learns to solve many tasks simultaneously but it also learns faster than agents that target a single task at-a-time. In some cases, where the single task DDPG method completely fails, the IU agent successfully solves the task. To demonstrate this, we build a playroom environment using the MuJoCo physics engine, and introduce a grounded formal language to automatically generate tasks.