- Rating
- 2
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
The paper studies long-horizon predictions in action-conditioned world models. It proposes DPWM, which encodes a variable-length action sequence using a Transformer to predict the endpoint latents directly. The complete pipeline is trained with endpoint reconstruction losses over sampled prediction horizons. Experiments evaluate DPWM through prediction error on four state-based continuous-control tasks from DeepMind Control Suite and a pixel-based Atari Game.
Critical strengths
- The idea of future prediction with a variable-length action sequence is appealing. To that end, the paper proposes a simple action sequence encoder and a dynamic model to predict the endpoint observation.
- The paper is easy to understand.
Critical weaknesses
- The contribution beyond prior work is insufficiently clarified. The paper emphasizes that "the training horizon, rather than the backbone alone, is a major driver of long-horizon prediction accuracy" (Line 29-31). However, it is common knowledge that training a model with supervision at longer horizons improves its prediction accuracy at correspondingly long test horizons. More importantly, the core idea of predicting a future outcome conditioned on an initial state and a variable-length action sequence has already been explored by ADM and ADM-v2. This concern is further amplified by the fact that DPWM predicts only the endpoint observation. Since the motivation for long-horizon world models is closely tied to planning and decision making, it would be important to explain how the proposed model is intended to support downstream policy evaluation or policy learning.
- The evaluation is too limited to establish a fair and practically meaningful comparison with prior world-model methods. The evaluation is almost entirely based on endpoint MSE. While these metrics directly measure the stated endpoint-prediction objective, they provide only a narrow view of world-model quality and make the reported results difficult to compare with the broader evaluation protocols used in closely related work. In particular, the main results in Table 2 are not fully controlled: DPWM is trained with , whereas ADM uses its short-horizon setting with , and the other recurrent baselines are trained with local one-step objectives. More importantly, all the compared baselines in the paper (i.e. DreamerV3, ADM-v2, and MoSim) evaluate long-horizon modeling in terms of downstream policy learning or policy evaluation rather than prediction error alone. ADM-v2, for example, reports off-policy evaluation on DOPE and policy optimization results on D4RL and NeoRL. In contrast, the current paper explicitly removes the actor–critic component when evaluating Dreamer and does not report any policy-level metric. Thus, it remains unclear whether the reduction in endpoint MSE translates into any meaningful improvement in planning, policy evaluation, or control performance.
Questions for authors
- Lines 413–415 state that the native frame is cropped to to remove the "static scoreboard region". However, the Pong scoreboard changes as the game progresses. Could the authors clarify the motivation for removing this region and whether this preprocessing is necessary?
- Table 2 reports endpoint prediction error in raw state space, whereas Table 3 reports MSE in normalized state space. Why are different evaluation spaces used? Please clarify whether the conclusions remain unchanged under a consistent metric.
- Which ADM or ADM-v2 implementation is used in each experiment? How are predictions beyond the model’s training horizon obtained?
- Figure 3 reports normalized training time, inference latency, and peak GPU memory. Could the authors also report the absolute peak memory in GB, training time, and inference latency at each evaluated horizon, together with the hardware configuration and model size?
- Lines 365–367 state that Table 3 is intended to isolate the effect of long-horizon training from the architectural choice. While ADM${}_{K=3}$ versus ADM$_{K=100}$ isolates the training-horizon effect within the same backbone, ADM$_{K=100}$ versus DPWM$_{K=100}$ may still differ in model capacity, optimization, and compute budget. Which factors are strictly controlled? Why is this comparison reported only on Humanoid?
- The paper motivates long-horizon world models in the context of planning and decision making, but evaluates DPWM almost exclusively using endpoint MSE. Why are established downstream protocols, such as policy evaluation or policy learning, not included?