A delivery fleet has a hard emission cap. Every route burns fuel. Every delivery creates value. The constraint is absolute: once the cap is reached, the fleet stops. The question is not which deliveries to make but which deliveries to refuse.
Tassel et al. (arXiv:2603.13279) formalize this as the Dynamic and Stochastic Vehicle Routing Problem with Emission Quota and show that reinforcement learning learns to reject profitable deliveries early in the day to preserve emission budget for later ones. The optimal policy says “no” to good orders now so it can say “yes” to better orders — or simply more orders — later. A myopic policy that accepts every profitable delivery until the cap binds will serve fewer total customers than one that strategically refuses from the start.
The mechanism is temporal asymmetry under a hard constraint. Early in the day, the fleet has budget but uncertainty about future demand. Late in the day, the fleet has information but may have exhausted its budget. A greedy policy converts budget to revenue as fast as possible, which means the late-day information arrives after the budget is gone. The RL agent learns the opposite: conserve budget through the uncertain period so that late-arriving, high-information decisions can still be acted on.
This is not the same as simple rationing, which would spread the budget evenly. The RL policy's rejections are non-uniform — it rejects specifically the orders whose emission cost is high relative to their value, or whose routing requires inefficient detours that consume disproportionate budget. The rejection is surgical, not proportional.
The through-claim: under a hard cumulative constraint, the value of a resource is not its current yield but its option value — the future decisions it keeps available. Accepting a good opportunity that consumes a shared resource can be strictly worse than refusing it, not because the opportunity is bad, but because accepting it forecloses better uses of the resource that have not yet appeared. The optimal policy under hard constraints must be anticipatorily conservative, and the conservatism concentrates in the high-uncertainty, low-information phase of the problem.