World–Action Coupling and Collection-Matched Optimization for Online Multi-Task Reinforcement Learning

Purely online multi-task reinforcement learning (MTRL) couples a global optimization clock to task-local data streams. With all-task updates at a fixed global frequency, task-wise update-to-data ratios can increase with the number of tasks. We introduce **WAM-MTRL-VE**, which couples latent future prediction to policy learning while matching task optimization to online data acquisition. The actor and an ensemble world model share a task-conditioned representation, and short imagined rollouts provide multi-step reward gradients to the actor through a frozen-model computation path. At each optimization tick, collection-matched stochastic optimization samples one replay-ready task according to the collection weights. Once all replay buffers are ready, matching update and collection probabilities recovers the nominal single-task update-to-data ratio in expectation while interleaving tasks. The entire agent is trained from scratch using online experience, without demonstrations or offline pretraining. On Meta-World, WAM-MTRL-VE reaches $96.2\%\pm 1.6\%$ success on MT10 after 1M total interactions per run, averaged over five training seeds. On MT50, a checkpoint selected from one 12M-interaction training run achieves $82.1\%\pm 0.5\%$ success across five independently seeded evaluation suites.