Temporal-difference error

Reinforcement learning · Formula · Not yet linked from a lesson

δt=rt+1+γV(st+1)−V(st)\delta_t = r_{t+1} + \gamma V(s_{t+1}) - V(s_t)

The gap between what you predicted and what the next step plus the next prediction say. It is the learning signal for every TD method, and it lets you learn from a single transition without waiting for the episode to end.

Symbols

δt\delta_t
The error at step t.
V(st)V(s_t)
The current prediction.
rt+1+γV(st+1)r_{t+1} + \gamma V(s_{t+1})
The one-step bootstrapped target.
Esc
↑↓ navigate↵ open? shortcuts

Keyboard shortcuts

Press Esc to close

Anywhere

⌘K
Search and commands
/
Search
?
This sheet
Esc
Close

Reading a lesson

J
Next lesson
K
Previous lesson
B
Bookmark