Task Relabelling for Multi-task Transfer using Successor Features

05/20/2022
by   Martin Balla, et al.
5

Deep Reinforcement Learning has been very successful recently with various works on complex domains. Most works are concerned with learning a single policy that solves the target task, but is fixed in the sense that if the environment changes the agent is unable to adapt to it. Successor Features (SFs) proposes a mechanism that allows learning policies that are not tied to any particular reward function. In this work we investigate how SFs may be pre-trained without observing any reward in a custom environment that features resource collection, traps and crafting. After pre-training we expose the SF agents to various target tasks and see how well they can transfer to new tasks. Transferring is done without any further training on the SF agents, instead just by providing a task vector. For training the SFs we propose a task relabelling method which greatly improves the agent's performance.

READ FULL TEXT
research
01/30/2019

Transfer in Deep Reinforcement Learning Using Successor Features and Generalised Policy Improvement

The ability to transfer skills across tasks has the potential to scale u...
research
10/29/2021

Xi-Learning: Successor Feature Transfer Learning for General Reward Functions

Transfer in Reinforcement Learning aims to improve learning performance ...
research
07/11/2023

Contextual Pre-Planning on Reward Machine Abstractions for Enhanced Transfer in Deep Reinforcement Learning

Recent studies show that deep reinforcement learning (DRL) agents tend t...
research
12/15/2016

Separation of Concerns in Reinforcement Learning

In this paper, we propose a framework for solving a single-agent task by...
research
11/13/2022

Build generally reusable agent-environment interaction models

This paper tackles the problem of how to pre-train a model and make it g...
research
06/24/2021

Towards Exploiting Geometry and Time for Fast Off-Distribution Adaptation in Multi-Task Robot Learning

We explore possible methods for multi-task transfer learning which seek ...
research
02/24/2023

Multi-Agent Reinforcement Learning with Common Policy for Antenna Tilt Optimization

This paper proposes a method for wireless network optimization applicabl...

Please sign up or login with your details

Forgot password? Click here to reset