2022 Conference on Cognitive Computational Neuroscience 2022
DOI: 10.32470/ccn.2022.1229-0
|View full text |Cite
|
Sign up to set email alerts
|

Continual Reinforcement Learning with Multi-Timescale Successor Features

Abstract: In Deep Reinforcement Learning (RL), it is a challenge to learn representations that do not exhibit catastrophic forgetting or interference in non-stationary environments. Successor Features (SFs) offer a potential solution to this challenge. However, canonical techniques for learning SFs from pixel-level observations often lead to representation collapse, wherein representations degenerate and fail to capture meaningful variations in the data. More recent methods for learning SFs can avoid representation coll… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1

Citation Types

0
1
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
1
1
1

Relationship

0
3

Authors

Journals

citations
Cited by 3 publications
(1 citation statement)
references
References 0 publications
0
1
0
Order By: Relevance
“…The successor representation (SR) (18) is a reinforcement learning algorithm specifically concerned with learning task structure based on a biologically plausible learning rule (19)(20)(21). Notably, it has been suggested that the successor representation can be leveraged to discover hierarchical representations (22,23). The successor representation learns a multi-step prediction of the task structure, which allows for fast and flexible behavior in the face of changing goals (24).…”
Section: Introductionmentioning
confidence: 99%
“…The successor representation (SR) (18) is a reinforcement learning algorithm specifically concerned with learning task structure based on a biologically plausible learning rule (19)(20)(21). Notably, it has been suggested that the successor representation can be leveraged to discover hierarchical representations (22,23). The successor representation learns a multi-step prediction of the task structure, which allows for fast and flexible behavior in the face of changing goals (24).…”
Section: Introductionmentioning
confidence: 99%