Emergence of Different Modes of Tool Use in a Reaching and Dragging Task

by   Khuong Nguyen, et al.

Tool use is an important milestone in the evolution of intelligence. In this paper, we investigate different modes of tool use that emerge in a reaching and dragging task. In this task, a jointed arm with a gripper must grab a tool (T, I, or L-shaped) and drag an object down to the target location (the bottom of the arena). The simulated environment had real physics such as gravity and friction. We trained a deep-reinforcement learning based controller (with raw visual and proprioceptive input) with minimal reward shaping information to tackle this task. We observed the emergence of a wide range of unexpected behaviors, not directly encoded in the motor primitives or reward functions. Examples include hitting the object to the target location, correcting error of initial contact, throwing the tool toward the object, as well as normal expected behavior such as wide sweep. Also, we further analyzed these behaviors based on the type of tool and the initial position of the target object. Our results show a rich repertoire of behaviors, beyond the basic built-in mechanisms of the deep reinforcement learning method we used.


page 4

page 5

page 6

page 7

page 9

page 10

page 11


Emergence of Human-comparable Balancing Behaviors by Deep Reinforcement Learning

This paper presents a hierarchical framework based on deep reinforcement...

Pathfinding in Random Partially Observable Environments with Vision-Informed Deep Reinforcement Learning

Deep reinforcement learning is a technique for solving problems in a var...

Towards Vision-Based Deep Reinforcement Learning for Robotic Motion Control

This paper introduces a machine learning based system for controlling a ...

Augmenting Reinforcement Learning with Behavior Primitives for Diverse Manipulation Tasks

Realistic manipulation tasks require a robot to interact with an environ...

Muscle Excitation Estimation in Biomechanical Simulation Using NAF Reinforcement Learning

Motor control is a set of time-varying muscle excitations which generate...

Learning Gentle Object Manipulation with Curiosity-Driven Deep Reinforcement Learning

Robots must know how to be gentle when they need to interact with fragil...

Predator-prey survival pressure is sufficient to evolve swarming behaviors

The comprehension of how local interactions arise in global collective b...

Please sign up or login with your details

Forgot password? Click here to reset