Giters
allentran
/
rl-l2t
Reinforcement learning paper + code: L2T
Geek Repo:
Geek Repo
Github PK Tool:
Github PK Tool
Stargazers:
Watchers:
2
Issues:
5
Forks:
1
allentran/rl-l2t Issues
Deep Q forward
Closed
9 years ago
Policy forward prop
Closed
9 years ago
Generate Policy gradients, wrt u, given sarsas, and Deep Q wrt and combine
Updated
9 years ago
Comments count
1
Generate Deep Q gradients (wrt w) from sample sarsas
Updated
9 years ago
Play policy forward with data, keep s, a, r, s', a'
Updated
9 years ago