Latent Planning via Embedding Arithmetic: A Contrastive Approach to Strategic Reasoning
Planning in high-dimensional decision spaces is increasingly being studied through the lens of learned representations. Rather than training policies or value heads, we investigate whether planning can be carried out directly in an evaluation-aligned embedding space. We introduce SOLIS, which learns such a space using supervised contrastive learning. In this representation, outcome similarity is captured by proximity, and a single global advantage vector orients the space from losing to winning regions. Candidate actions are then ranked according to their alignment with this direction, reducing planning to vector operations in latent space. We demonstrate this approach in chess, where SOLIS uses only a shallow search guided by the learned embedding to reach competitive strength under constrained conditions. More broadly, our results suggest that evaluation-aligned latent planning offers a lightweight alternative to traditional dynamics models or policy learning.
Code (0)
등록된 구현이 없습니다.
Tasks
Contrastive LearningSimilar Papers 제목 키워드 기반
Learning to Plan via Supervised Contrastive Learning and Strategic Interpolation: A Chess Case Study
Modern chess engines achieve superhuman performance through deep tree search and regressive evaluation, while human players rely on intuition to select candidate moves followed by a shallow search to validate them. To mo…
Contrastive LearningIt's Not a Modality Gap: Characterizing and Addressing the Contrastive Gap
Multi-modal contrastive models such as CLIP achieve state-of-the-art performance in zero-shot classification by embedding input images and texts on a joint representational space. Recently, a modality gap has been report…
image-classificationImage Classificationzero-shot-classificationZero-Shot Image Classification+1Hierarchical Text Generation and Planning for Strategic Dialogue
End-to-end models for goal-orientated dialogue are challenging to train, because linguistic and strategic aspects are entangled in latent state vectors. We introduce an approach to learning representations of messages in…
Decision Makingreinforcement-learningReinforcement LearningReinforcement Learning (RL)+2Reasoning as Energy Minimization over Structured Latent Trajectories
Single-shot neural decoders commit to answers without iterative refinement, while chain-of-thought methods introduce discrete intermediate steps but lack a scalar measure of reasoning progress. We propose Energy-Based Re…
Discrete Word Embedding for Logical Natural Language Understanding
We propose an unsupervised neural model for learning a discrete embedding of words. Unlike existing discrete embeddings, our binary embedding supports vector arithmetic operations similar to continuous embeddings. Our em…
Decision MakingNatural Language Understanding