# Task Relabelling for Multi-task Transfer using Successor Features

arXiv: https://arxiv.org/abs/2205.10175 · HTML: https://mlsanity.com/paper/2205.10175/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 21 references that are in the map.
- First posted on arXiv 20 May 2022.

## Builds on (most cited first, 11 of 11)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Hindsight Experience Replay](https://mlsanity.com/paper/1707.01495/) (2017)
- [Successor Features for Transfer in Reinforcement Learning](https://mlsanity.com/paper/1606.05312/) (2016)
- [Benchmarking the Spectrum of Agent Capabilities](https://mlsanity.com/paper/2109.06780/) (2021)
- [Fast Task Inference with Variational Intrinsic Successor Features](https://mlsanity.com/paper/1906.05030/) (2019)
- [Count-Based Exploration with the Successor Representation](https://mlsanity.com/paper/1807.11622/) (2018)
- [Universal Successor Features Approximators](https://mlsanity.com/paper/1812.07626/) (2018)
- [Deep Successor Reinforcement Learning](https://mlsanity.com/paper/1606.02396/) (2016)
- [The Option Keyboard: Combining Skills in Reinforcement Learning](https://mlsanity.com/paper/2106.13105/) (2021)
- [Augmenting Automated Game Testing with Deep Reinforcement Learning](https://mlsanity.com/paper/2103.15819/) (2021)
- [PsiPhi-Learning: Reinforcement Learning with Demonstrations using Successor Features and Inverse Temporal Difference Learning](https://mlsanity.com/paper/2102.12560/) (2021)

## Built on by (most cited first, 1 of 1)

- [Enhancing Two-Player Performance Through Single-Player Knowledge Transfer: An Empirical Study on Atari 2600 Games](https://mlsanity.com/paper/2410.16653/) (2024)

## Abstract (arXiv)

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.