Learning Novel Policies For Tasks

05/13/2019
by   Yunbo Zhang, et al.
0

In this work, we present a reinforcement learning algorithm that can find a variety of policies (novel policies) for a task that is given by a task reward function. Our method does this by creating a second reward function that recognizes previously seen state sequences and rewards those by novelty, which is measured using autoencoders that have been trained on state sequences from previously discovered policies. We present a two-objective update technique for policy gradient algorithms in which each update of the policy is a compromise between improving the task reward and improving the novelty reward. Using this method, we end up with a collection of policies that solves a given task as well as carrying out action sequences that are distinct from one another. We demonstrate this method on maze navigation tasks, a reaching task for a simulated robot arm, and a locomotion task for a hopper. We also demonstrate the effectiveness of our approach on deceptive tasks in which policy gradient methods often get stuck.

READ FULL TEXT
research
12/21/2020

Difference Rewards Policy Gradients

Policy gradient methods have become one of the most popular classes of a...
research
03/22/2019

Iterative Reinforcement Learning Based Design of Dynamic Locomotion Skills for Cassie

Deep reinforcement learning (DRL) is a promising approach for developing...
research
10/08/2021

Training Transition Policies via Distribution Matching for Complex Tasks

Humans decompose novel complex tasks into simpler ones to exploit previo...
research
05/04/2023

Causal Policy Gradient for Whole-Body Mobile Manipulation

Developing the next generation of household robot helpers requires combi...
research
03/02/2023

Co-learning Planning and Control Policies Using Differentiable Formal Task Constraints

This paper presents a hierarchical reinforcement learning algorithm cons...
research
06/21/2019

Entropic Risk Measure in Policy Search

With the increasing pace of automation, modern robotic systems need to a...
research
03/02/2023

T-Cell Receptor Optimization with Reinforcement Learning and Mutation Policies for Precesion Immunotherapy

T cells monitor the health status of cells by identifying foreign peptid...

Please sign up or login with your details

Forgot password? Click here to reset