BADGER: Learning to (Learn [Learning Algorithms] through Multi-Agent Communication)
arXiv:1912.01513
Abstract
In this work, we propose a novel memory-based multi-agent meta-learning architecture and learning procedure that allows for learning of a shared communication policy that enables the emergence of rapid adaptation to new and unseen environments by learning to learn learning algorithms through communication. Behavior, adaptation and learning to adapt emerges from the interactions of homogeneous experts inside a single agent. The proposed architecture should allow for generalization beyond the level seen in existing methods, in part due to the use of a single policy shared by all experts within the agent as well as the inherent modularity of 'Badger'.
References in corpus (28)
- Deep Reinforcement Learning for Multi-Agent Systems: A Review of Challenges, Solutions and Applications
- A Simple Neural Attentive Meta-Learner
- A Survey and Critique of Multiagent Deep Reinforcement Learning
- Learning to reinforcement learn
- QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning
- Learning Multiagent Communication with Backpropagation
- One Model To Learn Them All
- Emergence of Grounded Compositional Language in Multi-Agent Populations
- Paired Open-Ended Trailblazer (POET): Endlessly Generating Increasingly Complex and Diverse Learning Environments and Their Solutions
- Learned Optimizers that Scale and Generalize
- Learning to Adapt in Dynamic, Real-World Environments Through Meta-Reinforcement Learning
- Learning to Learn: Meta-Critic Networks for Sample Efficient Learning
- Meta-Learning Update Rules for Unsupervised Representation Learning
- Causal Reasoning from Meta-reinforcement Learning
- Autocurricula and the Emergence of Innovation from Social Interaction: A Manifesto for Multi-Agent Intelligence Research
- Improving Generalization in Meta Reinforcement Learning using Learned Objectives
- Meta reinforcement learning as task inference
- AI-GAs: AI-generating algorithms, an alternate paradigm for producing general artificial intelligence
- Understanding and correcting pathologies in the training of learned optimizers
- Backpropamine: training self-modifying neural networks with differentiable neuromodulated plasticity
- Meta-learning of Sequential Strategies
- Modular meta-learning
- Guided evolutionary strategies: Augmenting random search with surrogate gradients
- TarMAC: Targeted Multi-Agent Communication
- Meta-learners' learning dynamics are unlike learners'
- Learning to Communicate in Multi-Agent Reinforcement Learning : A Review
- Reinforcement Learning applied to Single Neuron
- Modular meta-learning in abstract graph networks for combinatorial generalization