- Rating
- 1
- Confidence
- 2
- Informativeness
- 1
- Presentation
- 2
- Soundness
- 1
Read review
Paper summary
The paper models the Social Motivation Theory of autism as a scalar weight on a peer-proximity reward in a dyadic version of the MPE simple_spread environment. Both agents share one PPO policy. Each agent is rewarded for proximity to the nearest landmark and, with weight , for proximity to its peer. is swept from full social reward down to near zero.
The paper reports that mean peer distance increases as falls which is expected and close to circular.
It also reports that a BiLSTM can classify from dyad trajectories, including after the distance features are removed, and that classification accuracy improves with longer observation windows before flattening. Finally, mixed- dyads coordinate slightly worse than matched ones, which the paper presents as an RL account of the Double Empathy Problem.
Critical strengths
Reasonable motivation. Existing RL models of autism are single-agent, and asking what changes when social reward is altered inside an interacting dyad is a fair question.
Critical weaknesses
The model has no meaningful connection to autism. The environment consists of a pair of point particles on a flat plane, with landmarks standing in for toys. Each particle is rewarded for being near the other, with that reward weighted by . Lowering makes the particles stay further apart.
This claimed behavioral result follows from the reward by construction. The agents are trained to reduce peer distance, so peer distance tracks . Calling this a "behavioral phenotype consistent with ASD" or a "computational biomarker" isn't supported.
Since the ML methods are off-the-shelf (PPO, MPE, BiLSTM), the paper's contribution depends entirely on this link to autism. Without that link, what remains is that agents rewarded for proximity stay close, which isn't an ICLR contribution.
The -recovery result likely measures policy identification rather than . The classifier section describes stratified cross-validation over trajectories and doesn't mention grouping by seed, so presumably every policy appears in both the training and test sets. If this is the case, the BiLSTM can learn each policy's idiosyncrasies and map them to a label without learning anything general about . Several results fit this explanation:
Without leave-one-seed-out evaluation, the reported accuracy can't be read as recovery of .
Questions for authors
-
Why is MPE simple_spread a suitable model environment for ASD? The agents are point particles rewarded for proximity to landmarks and to each other. Which aspects of autism does this capture, and what result could the model produce that isn't already determined by the reward function?
-
Were cross-validation folds split by trajectory or by seed? If by trajectory, what is the accuracy when entire policies are held out?
-
How were the mixed- dyads trained? If they used the shared policy, there is no agent ID or in the observation, so the network can't condition on . Both agents' updates would mix both reward signals, and the claim that each agent optimizes strictly under its own wouldn't hold.