Zobrazeno 1 - 10
of 26
pro vyhledávání: '"Morad, Steven"'
We present a method for developing navigation policies for multi-robot teams that interpret and follow natural language instructions. We condition these policies on embeddings from pretrained Large Language Models (LLMs), and train them via offline r
Externí odkaz:
http://arxiv.org/abs/2407.20164
Autonomous robot operation in unstructured environments is often underpinned by spatial understanding through vision. Systems composed of multiple concurrently operating robots additionally require access to frequent, accurate and reliable pose estim
Externí odkaz:
http://arxiv.org/abs/2405.01107
Existing communication methods for multi-agent reinforcement learning (MARL) in cooperative multi-robot problems are almost exclusively task-specific, training new communication strategies for each unique task. We address this inefficiency by introdu
Externí odkaz:
http://arxiv.org/abs/2403.06750
Autor:
Morad, Steven, Lu, Chris, Kortvelesy, Ryan, Liwicki, Stephan, Foerster, Jakob, Prorok, Amanda
Memory models such as Recurrent Neural Networks (RNNs) and Transformers address Partially Observable Markov Decision Processes (POMDPs) by mapping trajectories to latent Markov states. Neither model scales particularly well to long sequences, especia
Externí odkaz:
http://arxiv.org/abs/2402.09900
Nearly all real world tasks are inherently partially observable, necessitating the use of memory in Reinforcement Learning (RL). Most model-free approaches summarize the trajectory into a latent Markov state using memory models borrowed from Supervis
Externí odkaz:
http://arxiv.org/abs/2310.04128
Graph Neural Network (GNN) architectures are defined by their implementations of update and aggregation modules. While many works focus on new ways to parametrise the update modules, the aggregation modules receive comparatively little attention. Bec
Externí odkaz:
http://arxiv.org/abs/2306.13826
Real world applications of Reinforcement Learning (RL) are often partially observable, thus requiring memory. Despite this, partial observability is still largely ignored by contemporary RL benchmarks and libraries. We introduce Partially Observable
Externí odkaz:
http://arxiv.org/abs/2303.01859
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)
Externí odkaz:
http://arxiv.org/abs/2302.12826
GNNs are a paradigm-shifting neural architecture to facilitate the learning of complex multi-agent behaviors. Recent work has demonstrated remarkable performance in tasks such as flocking, multi-agent path planning and cooperative coverage. However,
Externí odkaz:
http://arxiv.org/abs/2111.01777
Solving partially-observable Markov decision processes (POMDPs) is critical when applying reinforcement learning to real-world problems, where agents have an incomplete view of the world. We present graph convolutional memory (GCM), the first hybrid
Externí odkaz:
http://arxiv.org/abs/2106.14117