# Diversity Through Exclusion (DTE): Niche Identification for Reinforcement Learning through Value-Decomposition

arXiv: https://arxiv.org/abs/2302.01180 · HTML: https://mlsanity.com/paper/2302.01180/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 48 references that are in the map.
- First posted on arXiv 2 Feb 2023.

## Builds on (most cited first, 23 of 23)

- [Curiosity-driven Exploration by Self-supervised Prediction](https://mlsanity.com/paper/1705.05363/) (2017)
- [Exploration by Random Network Distillation](https://mlsanity.com/paper/1810.12894/) (2018)
- [Diversity is All You Need: Learning Skills without a Reward Function](https://mlsanity.com/paper/1802.06070/) (2018)
- [QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/1803.11485/) (2018)
- [Deep Exploration via Bootstrapped DQN](https://mlsanity.com/paper/1602.04621/) (2016)
- [FeUdal Networks for Hierarchical Reinforcement Learning](https://mlsanity.com/paper/1703.01161/) (2017)
- [Dynamics-Aware Unsupervised Discovery of Skills](https://mlsanity.com/paper/1907.01657/) (2019)
- [Emergent Tool Use From Multi-Agent Autocurricula](https://mlsanity.com/paper/1909.07528/) (2019)
- [Agent57: Outperforming the Atari Human Benchmark](https://mlsanity.com/paper/2003.13350/) (2020)
- [Distributed Prioritized Experience Replay](https://mlsanity.com/paper/1803.00933/) (2018)
- [Variational Intrinsic Control](https://mlsanity.com/paper/1611.07507/) (2016)
- [Human-level performance in first-person multiplayer games with population-based deep reinforcement learning](https://mlsanity.com/paper/1807.01281/) (2018)
- [Multi-agent Reinforcement Learning in Sequential Social Dilemmas](https://mlsanity.com/paper/1702.03037/) (2017)
- [Intrinsic Motivation and Automatic Curricula via Asymmetric Self-Play](https://mlsanity.com/paper/1703.05407/) (2017)
- [Scalable Evaluation of Multi-Agent Reinforcement Learning with Melting Pot](https://mlsanity.com/paper/2107.06857/) (2021)
- [A multi-agent reinforcement learning model of common-pool resource appropriation](https://mlsanity.com/paper/1707.06600/) (2017)
- [The Option Keyboard: Combining Skills in Reinforcement Learning](https://mlsanity.com/paper/2106.13105/) (2021)
- [Real World Games Look Like Spinning Tops](https://mlsanity.com/paper/2004.09468/) (2020)
- [Diversity-Driven Exploration Strategy for Deep Reinforcement Learning](https://mlsanity.com/paper/1802.04564/) (2018)
- [Autocurricula and the Emergence of Innovation from Social Interaction: A Manifesto for Multi-Agent Intelligence Research](https://mlsanity.com/paper/1903.00742/) (2019)
- [Discovering Policies with DOMiNO: Diversity Optimization Maintaining Near Optimality](https://mlsanity.com/paper/2205.13521/) (2022)
- [Diversity-Inducing Policy Gradient: Using Maximum Mean Discrepancy to Find a Set of Diverse Policies](https://mlsanity.com/paper/1906.00088/) (2019)
- [Malthusian Reinforcement Learning](https://mlsanity.com/paper/1812.07019/) (2018)

## Built on by (most cited first, 2 of 2)

- [A Review of Cooperation in Multi-agent Learning](https://mlsanity.com/paper/2312.05162/) (2023)
- [A social path to human-like artificial intelligence](https://mlsanity.com/paper/2405.15815/) (2024)

## Abstract (arXiv)

Many environments contain numerous available niches of variable value, each associated with a different local optimum in the space of behaviors (policy space). In such situations it is often difficult to design a learning process capable of evading distraction by poor local optima long enough to stumble upon the best available niche. In this work we propose a generic reinforcement learning (RL) algorithm that performs better than baseline deep Q-learning algorithms in such environments with multiple variably-valued niches. The algorithm we propose consists of two parts: an agent architecture and a learning rule. The agent architecture contains multiple sub-policies. The learning rule is inspired by fitness sharing in evolutionary computation and applied in reinforcement learning using Value-Decomposition-Networks in a novel manner for a single-agent's internal population. It can concretely be understood as adding an extra loss term where one policy's experience is also used to update all the other policies in a manner that decreases their value estimates for the visited states. In particular, when one sub-policy visits a particular state frequently this decreases the value predicted for other sub-policies for going to that state. Further, we introduce an artificial chemistry inspired platform where it is easy to create tasks with multiple rewarding strategies utilizing different resources (i.e. multiple niches). We show that agents trained this way can escape poor-but-attractive local optima to instead converge to harder-to-discover higher value strategies in both the artificial chemistry environments and in simpler illustrative environments.