Temporal abstraction and generalisation in reinforcement learning
The ability of agents to generalise---to perform well when presented with previously unseen situations and data---is deeply important to the reliability, autonomy, and functionality of artificial intelligence systems. The generalisation test examines an agent's ability to reason over the world...
Main Author: | Smith, M |
---|---|
Other Authors: | Fellows, M |
Format: | Thesis |
Language: | English |
Published: |
2023
|
Subjects: |
Similar Items
-
Inductive biases and generalisation for deep reinforcement learning
by: Igl, M
Published: (2021) -
Towards robust reinforcement learning
by: Paul, S
Published: (2020) -
Understanding representation learning for deep reinforcement learning
by: Le Lan, C
Published: (2023) -
Bayesian and variational inference for reinforcement
learning
by: Fellows, M
Published: (2021) -
Exploration and value function factorisation in single and multi-agent reinforcement learning
by: Rashid, T
Published: (2021)