# tinker_cookbook.rl.RetryOnFailure

## _class_ [**tinker_cookbook.rl.RetryOnFailure**](https://github.com/thinking-machines-lab/tinker-cookbook/blob/main/tinker_cookbook/rl/rollout_strategy.py#L128) (_[RolloutStrategy](https://tinker-docs.thinking-machines.ai/cookbook/api-reference/rl/rolloutstrategy/)_)

Retry failed or timed-out trajectories with fresh environments.

When a trajectory fails (container crash, sandbox flake, transient error) or exceeds `per_rollout_timeout` seconds, a fresh env is created via `make_envs()` and the rollout is retried. This continues until either all trajectories succeed or the retry budget is exhausted.

If the retry budget is exhausted and a failure still occurs, the remaining in-flight tasks are cancelled and the exception is re-raised. This avoids partial-group bias from training on an incomplete set of trajectories.

Uses `asyncio.wait(FIRST_COMPLETED)` so retries start as soon as a failure is detected, without waiting for other in-flight rollouts.

**Fields:**

- [**max_retries**](https://github.com/thinking-machines-lab/tinker-cookbook/blob/main/tinker_cookbook/rl/rollout_strategy.py#L153) (_int_, default: `3`)
- [**per_rollout_timeout**](https://github.com/thinking-machines-lab/tinker-cookbook/blob/main/tinker_cookbook/rl/rollout_strategy.py#L154) (_float_, default: `0`)

### [**execute**](https://github.com/thinking-machines-lab/tinker-cookbook/blob/main/tinker_cookbook/rl/rollout_strategy.py#L160) (_env_group_builder_, _policy_)

Run rollouts with automatic retry on individual trajectory failures.

Creates environments, launches all rollouts concurrently, and retries any that fail (or time out) by creating a fresh environment. Uses `asyncio.wait(FIRST_COMPLETED)` so retries begin immediately upon detecting a failure.

**Parameters:**

- [**env_group_builder**](https://github.com/thinking-machines-lab/tinker-cookbook/blob/main/tinker_cookbook/rl/rollout_strategy.py#L162) (_[EnvGroupBuilder](https://tinker-docs.thinking-machines.ai/cookbook/api-reference/rl/envgroupbuilder/)_) – Builder used to create (and re-create on retry) environments for this rollout group.
- [**policy**](https://github.com/thinking-machines-lab/tinker-cookbook/blob/main/tinker_cookbook/rl/rollout_strategy.py#L163) (_[TokenCompleter](https://tinker-docs.thinking-machines.ai/cookbook/api-reference/completers/tokencompleter/)_) – The policy used to generate actions.

**Returns:** _RolloutResult_ – Result containing the successfully completed trajectories, surviving environments, and a list of any errors encountered (including retried ones).

**Raises:**

- Exception: Re-raises the failing exception when the retry budget is exhausted, after cancelling all remaining in-flight tasks.