Repository navigation
S25-F: reuse Harbor for agentic RL on Miles and verl (N10.1-10.4) - #274
Merged
Merged
Conversation
- yeto/rl/agentic: neutral AgentTask/TrialVerdict/AgentTrajectory, the OK/POLICY_LIMIT/ABORTED rule, trust checks, admission gate and harness metrics, the token recorder port and the turn join with alignment checks. - yeto/rl/harness/harbor: pinned harbor-miles-v0.20.0 commit, TrialConfig builder, TrialResult -> TrialVerdict, HarborHarness over Trial.run(); README compares the branch with Harbor 0.24.0 and lists the run steps. - Miles: agent function and reward hook that wrap Miles' Harbor example with the yeto outer layer (infrastructure failures are ABORTED, not 0). - verl: HarborAgentLoop(AgentLoopBase) registered as yeto_harbor, without changing verl or Harbor. - verl launcher and island entry refuse the Miles agentic flags instead of ignoring them. CPU tests only; no trajectory has run on a real sandbox yet. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Testing: Full remote test suite on the stack tip: 0 failures. Not validated on PPU/NPU hardware (machines busy).
Part of the S25 stack (NPU+PPU heterogeneous GLM5.3-Flash full-param RL). Draft; do not merge before the S24 stack (#262–#268).
🤖 Generated with Claude Code