mirror of
https://github.com/legop3/MultiRoombaRover.git
synced 2026-11-16 03:32:17 -05:00
better defaults
This commit is contained in:
@@ -529,16 +529,23 @@ Training defaults beneath `roverLearning.training`:
|
|||||||
| Setting | Default |
|
| Setting | Default |
|
||||||
|---|---:|
|
|---|---:|
|
||||||
| enabled (still gated by outer service enabled=false) | true |
|
| enabled (still gated by outer service enabled=false) | true |
|
||||||
| threads | 4 |
|
| threads | 8 |
|
||||||
| batchSize | 16 |
|
| batchSize | 16 |
|
||||||
| maxSamples / minimumSamples | 512 / 128 |
|
| maxSamples / minimumSamples | 1024 / 128 |
|
||||||
| passesPerJob | 2 |
|
| passesPerJob | 2 |
|
||||||
| roundsPerSession | 3 |
|
| roundsPerSession | 3 |
|
||||||
| maxStepsPerJob | 200 |
|
| maxStepsPerJob | 200 |
|
||||||
| checkpointEverySteps | 100 |
|
| checkpointEverySteps | 100 |
|
||||||
| intervalSeconds | 300 |
|
| intervalSeconds | 60 |
|
||||||
| maxJobSeconds | 600 |
|
| maxJobSeconds | 600 |
|
||||||
|
|
||||||
|
Defaults tuned to the user's dual E5-2620 v4 server benchmark: eight training
|
||||||
|
threads improved throughput substantially over four, while sixteen gave little
|
||||||
|
additional benefit. The larger sample pool and shorter interval are starting
|
||||||
|
choices for its available resources, not measured learning-quality improvements.
|
||||||
|
Inference remains four threads per rover. Existing explicit configuration values
|
||||||
|
override these defaults; this change does not rewrite deployed configuration.
|
||||||
|
|
||||||
At most four completed retained sessions are selected per job. Samples are spread
|
At most four completed retained sessions are selected per job. Samples are spread
|
||||||
over each full video via reservoir sampling, not always taken from its beginning.
|
over each full video via reservoir sampling, not always taken from its beginning.
|
||||||
The rounds limit is sampled training visits, not full passes over all recorded
|
The rounds limit is sampled training visits, not full passes over all recorded
|
||||||
|
|||||||
@@ -9,10 +9,10 @@ module.exports = {
|
|||||||
recording: { maxGiB: 20, minimumFreeGiB: 2, sessionSeconds: 300 },
|
recording: { maxGiB: 20, minimumFreeGiB: 2, sessionSeconds: 300 },
|
||||||
driving: { threads: 4, actionThreshold: 0.7, staleMs: 2000 },
|
driving: { threads: 4, actionThreshold: 0.7, staleMs: 2000 },
|
||||||
training: {
|
training: {
|
||||||
enabled: true, python: '/opt/rover-learning/bin/python', threads: 4,
|
enabled: true, python: '/opt/rover-learning/bin/python', threads: 8,
|
||||||
batchSize: 16, maxSamples: 512, minimumSamples: 128, passesPerJob: 2,
|
batchSize: 16, maxSamples: 1024, minimumSamples: 128, passesPerJob: 2,
|
||||||
roundsPerSession: 3, maxStepsPerJob: 200, checkpointEverySteps: 100,
|
roundsPerSession: 3, maxStepsPerJob: 200, checkpointEverySteps: 100,
|
||||||
intervalSeconds: 300, maxJobSeconds: 600,
|
intervalSeconds: 60, maxJobSeconds: 600,
|
||||||
},
|
},
|
||||||
},
|
},
|
||||||
schema: strictObject({
|
schema: strictObject({
|
||||||
|
|||||||
Reference in New Issue
Block a user