emer / axon

Axon is a spiking, biologically-based neural model driven by predictive error-driven learning, for systems-level models of the brain
BSD 3-Clause "New" or "Revised" License
20 stars 7 forks source link

approach env: don't set reward on forward #258

Closed garymm closed 1 year ago

garymm commented 1 year ago

Setting reward on forward doesn't make any sense. Doesn't seem to make a difference to key stats after 20 epochs.

And minor code simplification.

Change-Id: I6cdc6c3ee08a5d91444ce8bcfc10269549e5ddd6

codecov[bot] commented 1 year ago

Codecov Report

Patch coverage: 100.00% and project coverage change: -0.01 :warning:

Comparison is base (31cc3f3) 30.62% compared to head (9538994) 30.62%.

:exclamation: Current head 9538994 differs from pull request most recent head 021b7a8. Consider uploading reports for the commit 021b7a8 to get more accurate results

Additional details and impacted files ```diff @@ Coverage Diff @@ ## master #258 +/- ## ========================================== - Coverage 30.62% 30.62% -0.01% ========================================== Files 79 79 Lines 15157 15152 -5 ========================================== - Hits 4642 4640 -2 + Misses 10256 10255 -1 + Partials 259 257 -2 ``` | [Impacted Files](https://app.codecov.io/gh/emer/axon/pull/258?src=pr&el=tree&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=emer) | Coverage Δ | | |---|---|---| | [examples/boa/approach\_env.go](https://app.codecov.io/gh/emer/axon/pull/258?src=pr&el=tree&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=emer#diff-ZXhhbXBsZXMvYm9hL2FwcHJvYWNoX2Vudi5nbw==) | `92.20% <100.00%> (+1.10%)` | :arrow_up: |

:umbrella: View full report in Codecov by Sentry.
:loudspeaker: Do you have feedback about the report comment? Let us know in this issue.