Login / Signup
Decomposing user-defined tasks in a reinforcement learning setup using TextWorld.
Thanos Petsanis
Christoforos Keroglou
Athanasios Ch. Kapoutsis
Elias B. Kosmatopoulos
Georgios Ch. Sirakoulis
Published in:
Frontiers Robotics AI (2023)
Keyphrases
</>
user defined
reinforcement learning
data types
neural network
transfer learning
multi agent
database
state space
function approximation
real world
machine learning
learning algorithm
database management systems
optimal policy
optimal control