Login / Signup
Counterfactual rewards promote collective transport using individually controlled swarm microrobots.
Veit-Lorenz Heuthe
Emanuele Panizon
Hongri Gu
Clemens Bechinger
Published in:
CoRR (2024)
Keyphrases
</>
collective behavior
swarm intelligence
reinforcement learning
cooperative
collective intelligence
markov decision processes
particle swarm optimization
magnetic field
multiarmed bandit
bandit problems
long term and short term
databases
credit assignment
multi agent
image sequences
real world
neural network