TempoRL: Learning When to Act

TL;DR

TempoRL introduces a proactive reinforcement learning method that learns when to act and for how long, significantly improving learning efficiency by using skip policies to repeat actions over variable durations.

Contribution

It proposes a novel skip-connection approach with learned skip policies, enabling agents to decide action durations, which enhances learning speed in diverse environments.

Findings

Achieves up to tenfold faster learning than vanilla Q-learning.

Effective in both traditional and deep RL environments.

Demonstrates the benefit of proactive decision timing in reinforcement learning.

Abstract

Reinforcement learning is a powerful approach to learn behaviour through interactions with an environment. However, behaviours are usually learned in a purely reactive fashion, where an appropriate action is selected based on an observation. In this form, it is challenging to learn when it is necessary to execute new decisions. This makes learning inefficient, especially in environments that need various degrees of fine and coarse control. To address this, we propose a proactive setting in which the agent not only selects an action in a state but also for how long to commit to that action. Our TempoRL approach introduces skip connections between states and learns a skip-policy for repeating the same action along these skips. We demonstrate the effectiveness of TempoRL on a variety of traditional and deep RL environments, showing that our approach is capable of learning successful policies up to an order of magnitude faster than vanilla Q-learning.