A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Filters
Quantifying the effects of environment and population diversity in multi-agent reinforcement learning
[article]
2022
arXiv
pre-print
Preserved Fulltext
Other Versions
In this paper, we investigate and quantify the relationship between generalization and diversity in the multi-agent domain. ...
Generalization is a major challenge for multi-agent reinforcement learning. How well does an agent perform when placed in novel environments and in interactions with new co-players? ...
We are also indebted to Mary Cassin for designing and creating the sprite art for the DeepMind Lab2D implementation of Overcooked. ...
arXiv:2102.08370v2
fatcat:s2akt5hcbrhepdwefolq73yd4u
Effective Diversity in Population Based Reinforcement Learning
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Exploration is a key problem in reinforcement learning, since agents can only learn from data they acquire in the environment. ...
With that in mind, maintaining a population of agents is an attractive method, as it allows data be collected with a diverse set of behaviors. ...
The authors want to thank anonymous reviewers for constructive feedback which helped improve the paper. ...
arXiv:2002.00632v3
fatcat:5ayehk64rjd4tijxtuzwl4gh7e
Towards Learning Multi-agent Negotiations via Self-Play
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
In contrast, deep reinforcement learning (Deep RL) has been very effective at finding policies by simultaneously exploring, interacting, and learning from environments. ...
Leveraging the powerful Deep RL paradigm, we demonstrate that an iterative procedure of self-play can create progressively more diverse environments, leading to the learning of sophisticated and robust ...
Acknowledgements We thank Barry Theobald, Hanlin Goh, Ruslan Salakhutdinov, Jian Zhang, Nitish Srivastava, Alex Druinsky, and the anonymous reviewers for making this a better manuscript. ...
arXiv:2001.10208v1
fatcat:dp4ucamn5bektnd36ombdmxyfy
Towards Learning Multi-Agent Negotiations via Self-Play
2019
2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
In contrast, deep reinforcement learning (Deep RL) has been very effective at finding policies by simultaneously exploring, interacting, and learning from environments. ...
Leveraging the powerful Deep RL paradigm, we demonstrate that an iterative procedure of self-play can create progressively more diverse environments, leading to the learning of sophisticated and robust ...
Acknowledgements We thank Barry Theobald, Hanlin Goh, Ruslan Salakhutdinov, Jian Zhang, Nitish Srivastava, Alex Druinsky, and the anonymous reviewers for making this a better manuscript. ...
doi:10.1109/iccvw.2019.00297
dblp:conf/iccvw/Tang19
fatcat:5vyk4zkwcrdozmk3cfn75ttzpu
Giving Up Control: Neurons as Reinforcement Learning Agents
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
At the same time, they must cooperate, so the population and organism can perform high-level functions. To this end, we introduce modeling neurons as reinforcement learning agents. ...
Populations of neurons must compete with their neighbors for resources, inhibition, and activity representation. ...
This can be framed as neurons in the population composing the environment of other neurons. Figure 3 depicts the multi-agent network. ...
arXiv:2003.11642v1
fatcat:5qzfkdcys5hstd4cvnj6upy6pi
Co-Evolution of Predator-Prey Ecosystems by Reinforcement Learning Agents
2021
Entropy
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Here we frame the co-evolution of predators and preys in an ecosystem as allowing agents to learn and evolve toward better ones in a manner appropriate for multi-agent reinforcement learning. ...
The problem of finding adequate population models in ecology is important for understanding essential aspects of their dynamic nature. ...
Conflicts of Interest: The authors declare no conflict of interest. ...
doi:10.3390/e23040461
pmid:33924723
pmcid:PMC8069842
fatcat:44qbdgtbfnamfpy4bhyw4wby24
Pick Your Battles: Interaction Graphs as Population-Level Objectives for Strategic Diversity
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
We provide evidence for the importance of diversity in multi-agent training and analyse the effect of applying different interaction graphs on the training trajectories, diversity and performance of populations ...
In this paper we study how to construct diverse populations of agents by carefully structuring how individuals within a population interact. ...
Also related to our line of work is research on diversity in reinforcement learning, which is often studied in the context of intrinsic motivation and skill discovery [5, 8, 11, 13] . ...
arXiv:2110.04041v1
fatcat:fc54thv25jdtbakzfuxtqvt4de
Measuring Diversity in Populations Employing Cultural Learning in Dynamic Environments
[chapter]
2005
Lecture Notes in Computer Science
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
We compare the genotypic and phenotypic diversity of populations employing only population learning and of populations using both population and cultural learning in two types of dynamic environment: one ...
This paper examines the effect of cultural learning on a population of neural networks. ...
Acknowledgements This research is funded by the Irish Research Council for Science, Engineering and Technology. ...
doi:10.1007/11553090_39
fatcat:frgrojpucvfpfpdl7uhydj33oq
Emergent Coordination Through Competition
[article]
2019
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
We study the emergence of cooperative behaviors in reinforcement learning agents by introducing a challenging competitive multi-agent soccer environment with continuous simulated physics. ...
Our study highlights several of the challenges encountered in large scale multi-agent training in continuous control. ...
In any such game each agent in the population effectively treats the other agents as part of their environment and learns a policy π θ to optimize their expected return, averaged over such games. ...
arXiv:1902.07151v2
fatcat:dbhxgyk5lzb4zhhoflvjt642sy
Diverse Behavior Is What Game AI Needs: Generating Varied Human-Like Playing Styles Using Evolutionary Multi-Objective Deep Reinforcement Learning
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2020 pre-print arXiv:1910.09022v2 fatcat:xkzodr42uvdb3oao4grycra77uOther Versions
This demonstrates the effectiveness of EMO-DRL in learning complex style automatically. ...
In the beginning, EMO-DRL initializes and maintains a population of candidates (black dots). ...
arXiv:1910.09022v6
fatcat:aolmaskxsberdfyofof2j4z3hu
Dynamics-aware novelty search with behavior repulsion
2022
Proceedings of the Genetic and Evolutionary Computation Conference
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Searching solutions for the task with sparse or deceptive rewards is a fundamental problem in Evolutionary Algorithms (EA) and Reinforcement Learning (RL). ...
The novelty of a single solution is defined as the prediction error of an approximate dynamic model in the task-agnostic behavior space. ...
As a promising policy search method in recent years, Reinforcement Learning agents can typically only learn from experience acquired in the environment, making training policy with deceptive or sparse ...
doi:10.1145/3512290.3528761
fatcat:ocwbnxzqana4xazfctsr6gezbm
Diverse Auto-Curriculum is Critical for Successful Real-World Multiagent Learning Systems
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Multiagent reinforcement learning (MARL) has achieved a remarkable amount of success in solving various types of video games. ...
A cornerstone of this success is the auto-curriculum framework, which shapes the learning process by continually creating new challenging tasks for agents to adapt to, thereby facilitating the acquisition ...
Challenges include the lack of an accurate simulator [13] , the high cost of environmental interaction, and the difficulty in learning both effective and diverse policies. ...
arXiv:2102.07659v2
fatcat:nlijvc7yizflvdz5iqxibw4tfa
Policy-focused Agent-based Modeling using RL Behavioral Models
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
This paper examines the value of reinforcement learning (RL) models as adaptive, high-performing, and behaviorally-valid models of agent decision-making in ABMs. ...
We run some analytic experiments on our AI-equipped ABMs e.g. explorations of the effects of behavioral heterogeneity in a population and the emergence of synchronization in a population. ...
A good ABM can enable policy analysts and decision-makers to explore the potential macro-effects of diverse policy interventions on a population of real-world agents. ...
arXiv:2006.05048v3
fatcat:2xdlvcxtajfu5ekpj2zhqzmnai
An Introduction to Multi-Agent Reinforcement Learning and Review of its Application to Autonomous Mobility
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Recent advances in behavioral planning use Reinforcement Learning to find effective and performant behavior strategies. ...
Multi-Agent Reinforcement Learning (MARL) is a research field that aims to find optimal solutions for multiple agents that interact with each other. ...
MULTI-AGENT REINFORCEMENT LEARNING In MARL, multiple agents are concurrently optimized to find optimal policies. ...
arXiv:2203.07676v2
fatcat:jedez77btbehzmlsahfl6x56wm
Embodied intelligence via learning and evolution
2021
Nature Communications
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
The intertwined processes of learning and evolution in complex environmental niches have resulted in a remarkable diversity of morphological forms. ...
Here, we introduce Deep Evolutionary Reinforcement Learning (DERL): a computational framework which can evolve diverse agent morphologies to learn challenging locomotion and manipulation tasks in complex ...
In addition, the repository also includes code for creating UNIMALS, generating evolutionary environments, and evaluation task suite. ...
doi:10.1038/s41467-021-25874-z
pmid:34615862
fatcat:x32gdnis45b2zbia7zvaxc5ahi
« Previous
Showing results 1 — 15 out of 21,149 results