Action-modulated midbrain dopamine activity arises from distributed control policies.

Jack Lindsey Ashok Litwin-Kumar

Published in: NeurIPS (2022)

Keyphrases

control policies
action space
cooperative
optimal policy
stochastic optimization problems
reinforcement learning
multi agent
control system
state space
mobile robot
real time
control policy
random walk
finite horizon
control strategies
markov decision processes
model checking
vision system
neural network