Learning-Free Methods for Goal Conditioned Reinforcement Learning from Images
Abstract
We are interested in training goal-conditioned reinforcement learning agents to reach arbitrary goals specified as images. In order to make our agent fully general, we provide the agent with only images of the environment and the goal image. Prior methods in goal-conditioned reinforcement learning from images use a learned lower-dimensional representation of images. These learned latent representations are not necessary to solve a variety of goal-conditioned tasks from images. We show that a goal-conditioned reinforcement learning policy can be successfully trained end-to-end from pixels by using simple reward functions. In contrast to prior work, we demonstrate that using negative raw pixel distance as a reward function is a strong baseline. We also show that using the negative Euclidian distance between feature vectors produced by a random convolutional neural network outperforms learned latent representations like convolutional variational autoencoders.
Collections
Cite this version of the work
Alexander Van de Kleut
(2021).
Learning-Free Methods for Goal Conditioned Reinforcement Learning from Images. UWSpace.
http://hdl.handle.net/10012/16908
Other formats
Related items
Showing items related by title, author, creator and subject.
-
Asking for Help with a Cost in Reinforcement Learning
Vandenhof, Colin (University of Waterloo, 2020-05-15)Reinforcement learning (RL) is a powerful tool for developing intelligent agents, and the use of neural networks makes RL techniques more scalable to challenging real-world applications, from task-oriented dialogue systems ... -
Multi-Agent Reinforcement Learning in Large Complex Environments
Ganapathi Subramanian, Sriram (University of Waterloo, 2022-07-15)Multi-agent reinforcement learning (MARL) has seen much success in the past decade. However, these methods are yet to find wide application in large-scale real world problems due to two important reasons. First, MARL ... -
Learning From Almost No Data
Sucholutsky, Ilia (University of Waterloo, 2021-06-15)The tremendous recent growth in the fields of artificial intelligence and machine learning has largely been tied to the availability of big data and massive amounts of compute. The increasingly popular approach of training ...