- Rating
- 1
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 1
- Soundness
- 1
Read review
Paper summary
The paper presents behavior structure, an approach that treats action-conditioned relations between states as representation units for decision making and solving tasks by composing these local relations. Instead of modeling behavior from a trajectory-centered perspective, behavior structure exploits reusable local structures and builds a weighted graph structure to facilitate goal-directed planning. The experiments show that the proposed method outperforms the baselines on two simulated tasks and remains effective under withheld-boundary evaluations. Ablation studies further stress the importance of modeling action-conditioned relation costs for shortest-path planning over the behavior structure.
Critical strengths
- The paper proposes a new modeling perspective for offline decision making. Rather than treating complete trajectories as the primary units, behavior structure instead builds on action-conditioned local relations between states and enables graph-based planning using learned relation costs as edge weights. This formulation could construct behaviors that are not observed as complete trajectories.
- Withheld-boundary experiments demonstrate the effectiveness of the methods in utilizing local behavior for planning.
Critical weaknesses
- Several important details are missing in the method and require further elaboration. (1) how is trained to obtain transition-supervised representation? Is it trained separately via contrastive learning or end-to-end with ? (2) Are the 12 nearest neighbors selected in Section 3.2 treated as positive targets for training in Section 3.3, or can they be incidentally sampled as negative targets? (3) How are the upper and lower bounds (i.e., 0 and 3) decided for the clip function in Section 3.3?
- The standard goal-directed evaluation in Section 4.2 focuses on only two simulated tasks with low-dimensional state input, and compares against one baseline and its goal-conditioned variant. The controlled composition test instead compares against another baseline method. Consistent evaluation settings and additional results on more challenging tasks and more recent baselines (e.g., models that stitch sub-trajectories via RL or generative models) are critical to strengthen the experiments.
- See the questions below.
Questions for authors
- The standard evaluation tests the method at different target horizons. However, Table 1 only provides aggregated results. How do the proposed methods and the baselines perform under different target horizons? Would the method be able to tackle more complicated tasks with target horizons beyond the evaluated range?
- How does the number of sampled nearest-neighbor states (e.g., K=12 used in the method) affect the performance?
- What’s the inference cost for running Dijkstra over the constructed graph? How does it compare to baseline methods that do not rely on graph-based planning?