On Simple Reactive Neural Networks for Behaviour-Based Reinforcement Learning

by   Ameya Pore, et al.

We present a behaviour-based reinforcement learning approach, inspired by Brook's subsumption architecture, in which simple fully connected networks are trained as reactive behaviours. Our working assumption is that a pick and place robotic task can be simplified by leveraging domain knowledge of a robotics developer to decompose and train such reactive behaviours; namely, approach, grasp, and retract. Then the robot autonomously learns how to combine them via an Actor-Critic architecture. The Actor-Critic policy is to determine the activation and inhibition mechanisms of the reactive behaviours in a particular temporal sequence. We validate our approach in a simulated robot environment where the task is picking a block and taking it to a target position while orienting the gripper from a top grasp. The latter represents an extra degree-of-freedom of which current end-to-end reinforcement learning fail to generalise. Our findings suggest that robotic learning can be more effective if each behaviour is learnt in isolation and then combined them to accomplish the task. That is, our approach learns the pick and place task in 8,000 episodes, which represents a drastic reduction in the number of training episodes required by an end-to-end approach and the existing state-of-the-art algorithms.


page 1

page 4


Hybrid Actor-Critic Reinforcement Learning in Parameterized Action Space

In this paper we propose a hybrid architecture of actor-critic algorithm...

A Deep Learning Approach to Grasping the Invisible

We introduce a new problem named "grasping the invisible", where a robot...

Intrinsic Robotic Introspection: Learning Internal States From Neuron Activations

We present an introspective framework inspired by the process of how hum...

Neural Coreference Resolution based on Reinforcement Learning

The target of a coreference resolution system is to cluster all mentions...

Deep Reinforcement Learning with Dynamic Optimism

In recent years, deep off-policy actor-critic algorithms have become a d...

Learning to Grasp on the Moon from 3D Octree Observations with Deep Reinforcement Learning

Extraterrestrial rovers with a general-purpose robotic arm have many pot...

Survivable Hyper-Redundant Robotic Arm with Bayesian Policy Morphing

In this paper we present a Bayesian reinforcement learning framework tha...

Please sign up or login with your details

Forgot password? Click here to reset