Supplementary Material for Curious Exploration via Structured World Models Yields Zero-Shot Object Manipulation A GNN Architectural Details

We use message-passing GNNs in CEE-US as described in Sec. In a generalized setup, the sum in Eq. 1 can be replaced with another permutation-invariant function In this section, we provide experimental details and hyperparameter settings. Note that we overload the superscript to both indicate ensemble members' predictions and object-centric Note that model learning only occurs during the intrinsic phase. C.3.1 Details on Downstream T asks and Reward Functions We use the notation introduced in Sec. The actuated agent, i.e. robot, state is given by Each goal site is at least 0.16 and at most 0.20 away from the manipulability range of the robot arm.