Search Results for author:
Found 5 papers, 5 papers with code
Generalising Multi-Agent Cooperation through Task-Agnostic Communication
Our objective is to learn a fixed-size latent Markov state from a variable number of agent observations.
Revisiting Recurrent Reinforcement Learning with Memory Monoids
Memory models such as Recurrent Neural Networks (RNNs) and Transformers address Partially Observable Markov Decision Processes (POMDPs) by mapping trajectories to latent Markov states.
POPGym: Benchmarking Partially Observable Reinforcement Learning
Real world applications of Reinforcement Learning (RL) are often partially observable, thus requiring memory.
Permutation-Invariant Set Autoencoders with Fixed-Size Embeddings for Multi-Agent Learning
The problem of permutation-invariant learning over set representations is particularly relevant in the field of multi-agent systems -- a few potential applications include unsupervised training of aggregation functions in graph neural networks (GNNs), neural cellular automata on graphs, and prediction of scenes with multiple objects.
A Framework for Real-World Multi-Robot Systems Running Decentralized GNN-Based Policies
We demonstrate our framework on a case-study that requires tight coordination between robots, and present first-of-a-kind results that show successful real-world deployment of GNN-based policies on a decentralized multi-robot system relying on Adhoc communication.
