Totally model-free actor-critic recurrent neural-network reinforcement learning in non-Markovian domains (Q1699932): Difference between revisions
From MaRDI portal
Removed claim: author (P16): Item:Q773401 |
Changed an Item |
||
| Property / author | |||
| Property / author: Stuart E. Dreyfus / rank | |||
Normal rank | |||
Revision as of 22:26, 20 February 2024
scientific article
| Language | Label | Description | Also known as |
|---|---|---|---|
| English | Totally model-free actor-critic recurrent neural-network reinforcement learning in non-Markovian domains |
scientific article |
Statements
Totally model-free actor-critic recurrent neural-network reinforcement learning in non-Markovian domains (English)
0 references
26 February 2018
0 references
actor-critic reinforcement learning
0 references
recurrent neural networks
0 references
non-Markovian dependencies
0 references
