Diffusion-MPC in Discrete Domains: Feasibility Constraints, Horizon Effects, and Critic Alignment: Case study with Tetris
Fuente:
arXiv
Enregistré dans:
| Auteur principal: | |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866915830285991936 |
|---|---|
| author | Wang, Haochuan Kevin |
| author_facet | Wang, Haochuan Kevin |
| contents | We study diffusion-based model predictive control (Diffusion-MPC) in discrete combinatorial domains using Tetris as a case study. Our planner samples candidate placement sequences with a MaskGIT-style discrete denoiser and selects actions via reranking. We analyze three key factors: (1) feasibility-constrained sampling via logit masking over valid placements, (2) reranking strategies using a heuristic score, a pretrained DQN critic, and a hybrid combination, and (3) compute scaling in candidate count and planning horizon. We find that feasibility masking is necessary in discrete domains, removing invalid action mass (46%) and yielding a 6.8% improvement in score and 5.6% improvement in survival over unconstrained sampling. Naive DQN reranking is systematically misaligned with rollout quality, producing high decision regret (mean 17.6, p90 36.6). Shorter planning horizons outperform longer ones under sparse and delayed rewards, suggesting uncertainty compounding in long imagined rollouts. Overall, compute choices (K, H) determine dominant failure modes: small K limits candidate quality, while larger H amplifies misranking and model mismatch. Our findings highlight structural challenges of diffusion planners in discrete environments and provide practical diagnostics for critic integration. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_02348 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Diffusion-MPC in Discrete Domains: Feasibility Constraints, Horizon Effects, and Critic Alignment: Case study with Tetris Wang, Haochuan Kevin Machine Learning Artificial Intelligence Robotics 68T05, 68T20 I.2.6; I.2.8; F.2.2 We study diffusion-based model predictive control (Diffusion-MPC) in discrete combinatorial domains using Tetris as a case study. Our planner samples candidate placement sequences with a MaskGIT-style discrete denoiser and selects actions via reranking. We analyze three key factors: (1) feasibility-constrained sampling via logit masking over valid placements, (2) reranking strategies using a heuristic score, a pretrained DQN critic, and a hybrid combination, and (3) compute scaling in candidate count and planning horizon. We find that feasibility masking is necessary in discrete domains, removing invalid action mass (46%) and yielding a 6.8% improvement in score and 5.6% improvement in survival over unconstrained sampling. Naive DQN reranking is systematically misaligned with rollout quality, producing high decision regret (mean 17.6, p90 36.6). Shorter planning horizons outperform longer ones under sparse and delayed rewards, suggesting uncertainty compounding in long imagined rollouts. Overall, compute choices (K, H) determine dominant failure modes: small K limits candidate quality, while larger H amplifies misranking and model mismatch. Our findings highlight structural challenges of diffusion planners in discrete environments and provide practical diagnostics for critic integration. |
| title | Diffusion-MPC in Discrete Domains: Feasibility Constraints, Horizon Effects, and Critic Alignment: Case study with Tetris |
| topic | Machine Learning Artificial Intelligence Robotics 68T05, 68T20 I.2.6; I.2.8; F.2.2 |
| url | https://arxiv.org/abs/2603.02348 |