11 lines
204 B
Plaintext
11 lines
204 B
Plaintext
uint16 nr_weights
|
|
uint16 max_steps
|
|
uint16 nr_episodes
|
|
uint16 nr_runs
|
|
string acquisition_function
|
|
float32 epsilon
|
|
---
|
|
float32[] best_policy
|
|
float32[] best_weights
|
|
float32[] reward_mean
|
|
float32[] reward_std |