Automatic Goal Generation for Reinforcement Learning Agents

05/17/2017
by   David Held, et al.
0

Reinforcement learning is a powerful technique to train an agent to perform a task. However, an agent that is trained using reinforcement learning is only capable of achieving the single task that is specified via its reward function. Such an approach does not scale well to settings in which an agent needs to perform a diverse set of tasks, such as navigating to varying positions in a room or moving objects to varying locations. Instead, we propose a method that allows an agent to automatically discover the range of tasks that it is capable of performing. We use a generator network to propose tasks for the agent to try to achieve, specified as goal states. The generator network is optimized using adversarial training to produce tasks that are always at the appropriate level of difficulty for the agent. Our method thus automatically produces a curriculum of tasks for the agent to learn. We show that, by using this framework, an agent can efficiently and automatically learn to perform a wide set of tasks without requiring any prior knowledge of its environment. Our method can also learn to achieve tasks with sparse rewards, which traditionally pose significant challenges.

READ FULL TEXT

page 7

page 8

research
07/17/2017

Reverse Curriculum Generation for Reinforcement Learning

Many relevant tasks require an agent to reach a certain state, or to man...
research
03/27/2018

Forward-Backward Reinforcement Learning

Goals for reinforcement learning problems are typically defined through ...
research
08/09/2017

Decoupled Learning of Environment Characteristics for Safe Exploration

Reinforcement learning is a proven technique for an agent to learn a tas...
research
04/30/2023

Incremental procedural and sensorimotor learning in cognitive humanoid robots

The ability to automatically learn movements and behaviors of increasing...
research
07/01/2020

Adaptive Procedural Task Generation for Hard-Exploration Problems

We introduce Adaptive Procedural Task Generation (APT-Gen), an approach ...
research
07/04/2018

Region Growing Curriculum Generation for Reinforcement Learning

Learning a policy capable of moving an agent between any two states in t...
research
06/18/2012

Artist Agent: A Reinforcement Learning Approach to Automatic Stroke Generation in Oriental Ink Painting

Oriental ink painting, called Sumi-e, is one of the most appealing paint...

Please sign up or login with your details

Forgot password? Click here to reset