Full gradient DQN reinforcement learning: a provably convergent scheme (Q5153609)
From MaRDI portal
!
This is the item page for this Wikibase entity, intended for internal use and editing purposes. Please use the normal view instead:
scientific article; zbMATH DE number 7404789
| Language | Label | Description | Also known as |
|---|---|---|---|
| default for all languages | No label defined |
||
| English | Full gradient DQN reinforcement learning: a provably convergent scheme |
scientific article; zbMATH DE number 7404789 |
Statements
Full Gradient DQN Reinforcement Learning: A Provably Convergent Scheme (English)
0 references
30 September 2021
0 references
Markov decision process (MDP)
0 references
approximate dynamic programming
0 references
deep reinforcement learning (DRL)
0 references
stochastic approximation
0 references
deep Q-network (DQN)
0 references
full gradient DQN
0 references
Bellman error minimization
0 references
0 references
0 references
0.7467197179794312
0 references
0.7376719117164612
0 references
0.7288627028465271
0 references
0.7217490077018738
0 references
0.7169418931007385
0 references
