diff options
Diffstat (limited to 'BABYAI_SHARED_FEEDBACK.md')
| -rw-r--r-- | BABYAI_SHARED_FEEDBACK.md | 16 |
1 files changed, 16 insertions, 0 deletions
diff --git a/BABYAI_SHARED_FEEDBACK.md b/BABYAI_SHARED_FEEDBACK.md index e214ead..9443253 100644 --- a/BABYAI_SHARED_FEEDBACK.md +++ b/BABYAI_SHARED_FEEDBACK.md @@ -168,3 +168,19 @@ If no candidate is eligible, raw and SDIL are not run on this architecture; the next method change must supply task memory rather than tune shared-feedback strength. If P0 passes, the chosen configuration enters the same 40-epoch, three-seed BP/clean-KP/raw/SDIL comparison as B1. + +## P0 outcome + +All eight runs were finite, but no feedforward candidate passed. The best BP +rollout success was `63.6%` (four layers, learning rate `0.03`) and the best +clean-KP success was `52.2%` at the same setting, below the frozen `70%` and +`60%` thresholds. Their expert-action accuracies were `84.81%` and `83.84%`. +Removing the mission reduced the best BP policy to `11.6%` success, confirming +that this task depends on the language signal. Raw and SDIL were not run. + +The next clean-only feasibility stage keeps the best P0 depth and learning rate +and adds a fixed basal history of observations and previous actions. It tests +history lengths four and eight for 25 epochs, using only BP and clean KP. The +same `70%` BP, `60%` clean-KP, and 20-point BP mission-lesion thresholds apply; +ties favor the shorter history. This changes the missing state information, +not the shared-feedback signal or its strength. |