OptLayer - Practical Constrained Optimization for Deep Reinforcement Learning in the Real World

by   Tu-Hoa Pham, et al.

While deep reinforcement learning techniques have recently produced considerable achievements on many decision-making problems, their use in robotics has largely been limited to simulated worlds or restricted motions, since unconstrained trial-and-error interactions in the real world can have undesirable consequences for the robot or its environment. To overcome such limitations, we propose a novel reinforcement learning architecture, OptLayer, that takes as inputs possibly unsafe actions predicted by a neural network and outputs the closest actions that satisfy chosen constraints. While learning control policies often requires carefully crafted rewards and penalties while exploring the range of possible actions, OptLayer ensures that only safe actions are actually executed and unsafe predictions are penalized during training. We demonstrate the effectiveness of our approach on robot reaching tasks, both simulated and in the real world.



There are no comments yet.


page 1

page 7

page 8


Learning to Walk via Deep Reinforcement Learning

Deep reinforcement learning suggests the promise of fully automated lear...

Cat-like Jumping and Landing of Legged Robots in Low-gravity Using Deep Reinforcement Learning

In this article, we show that learned policies can be applied to solve l...

Passing Through Narrow Gaps with Deep Reinforcement Learning

The DARPA subterranean challenge requires teams of robots to traverse di...

Reward-Based Environment States for Robot Manipulation Policy Learning

Training robot manipulation policies is a challenging and open problem i...

DAQN: Deep Auto-encoder and Q-Network

The deep reinforcement learning method usually requires a large number o...

I am Robot: Neuromuscular Reinforcement Learning to Actuate Human Limbs through Functional Electrical Stimulation

Human movement disorders or paralysis lead to the loss of control of mus...

A Deep Reinforcement Learning Chatbot

We present MILABOT: a deep reinforcement learning chatbot developed by t...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.