# TD-M(PC)2: Improving Temporal Difference MPC Through Policy Constraint

arXiv: https://arxiv.org/abs/2502.03550 · HTML: https://mlsanity.com/paper/2502.03550/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Placed in RL theory and sample complexity, one of 15 directions in Deep reinforcement learning methods.
- First posted on arXiv 5 Feb 2025.

## Placed in

- Deep reinforcement learning methods / [RL theory and sample complexity](https://mlsanity.com/deeprl/rl-theory-and-sample-complexity/)

## Built on by (most cited first, 14 of 14)

- [Learning Massively Multitask World Models for Continuous Control](https://mlsanity.com/paper/2511.19584/) (2025)
- [Bootstrap Off-policy with World Model](https://mlsanity.com/paper/2511.00423/) (2025)
- [The Surprising Difficulty of Search in Model-Based Reinforcement Learning](https://mlsanity.com/paper/2601.21306/) (2026)
- [Residual Policy Gradient: A Reward View of KL-regularized Objective](https://mlsanity.com/paper/2503.11019/) (2025)
- [A KL-regularization Framework for Learning to Plan with Adaptive Priors](https://mlsanity.com/paper/2510.04280/) (2025)
- [EfficientTDMPC: Improved MPC Objectives for Sample-Efficient Continuous Control](https://mlsanity.com/paper/2605.16692/) (2026)
- [Dream-MPC: Gradient-Based Model Predictive Control with Latent Imagination](https://mlsanity.com/paper/2605.04568/) (2026)
- [CAST: Alternating State-Value Targets and Expanded Policy Gradients for Model-Based Reinforcement Learning](https://mlsanity.com/paper/2609.08853/) (2026)
- [RAY-TOLD: Ray-Based Latent Dynamics for Dense Dynamic Obstacle Avoidance with TDMPC](https://mlsanity.com/paper/2604.27450/) (2026)
- [Scaling World-Model Reinforcement Learning Through Diffusion Policy Optimization](https://mlsanity.com/paper/2605.26282/) (2026)
- [V-Simba: Unleashing the Architectural Potential of RL in Visual Continuous Control](https://mlsanity.com/paper/2608.07870/) (2026)
- [GEM-MPC: Balancing Exploration and Exploitation through Expert-Guided Planning](https://mlsanity.com/paper/2609.21735/) (2026)
- [Think Fast, Plan Selectively: Adaptive Deliberation for Efficient Data-Driven MPC](https://mlsanity.com/paper/2609.32591/) (2026)
- [Chunk-wise Model-based Policy Optimization](https://mlsanity.com/paper/2610.14564/) (2026)

## Abstract (arXiv)

Model-based reinforcement learning algorithms that combine model-based planning and learned value/policy prior have gained significant recognition for their high data efficiency and superior performance in continuous control. However, we discover that existing methods that rely on standard SAC-style policy iteration for value learning, directly using data generated by the planner, often result in persistent value overestimation. Through theoretical analysis and experiments, we argue that this issue is deeply rooted in the structural policy mismatch between the data generation policy that is always bootstrapped by the planner and the learned policy prior. To mitigate such a mismatch in a minimalist way, we propose a policy regularization term reducing out-of-distribution (OOD) queries, thereby improving value learning. Our method involves minimum changes on top of existing frameworks and requires no additional computation. Extensive experiments demonstrate that the proposed approach improves performance over baselines such as TD-MPC2 by large margins, particularly in 61-DoF humanoid tasks. View qualitative results at https://darthutopian.github.io/tdmpcsquare/.