REVIEW 33 cited by
Temporal Difference Learning for Model Predictive Control
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Temporal Difference Learning for Model Predictive Control
read the original abstract
Data-driven model predictive control has two key advantages over model-free methods: a potential for improved sample efficiency through model learning, and better performance as computational budget for planning increases. However, it is both costly to plan over long horizons and challenging to obtain an accurate model of the environment. In this work, we combine the strengths of model-free and model-based methods. We use a learned task-oriented latent dynamics model for local trajectory optimization over a short horizon, and use a learned terminal value function to estimate long-term return, both of which are learned jointly by temporal difference learning. Our method, TD-MPC, achieves superior sample efficiency and asymptotic performance over prior work on both state and image-based continuous control tasks from DMControl and Meta-World. Code and video results are available at https://nicklashansen.github.io/td-mpc.
Forward citations
Cited by 33 Pith papers
-
When Is a Learned Command Adapter Worth It? Closed-Loop Identification and Counterfactual Auditing of Frozen Locomotion Policies
A counterfactual audit separates same-state headroom from recoverable state-allocation gain, returning NO-GO or ABSTAIN for learned command adapters on frozen Go2 and H1 locomotion policies at 1% thresholds.
-
MiraBench: Evaluating Action-Conditioned Reliability in Robotic World Models
MiraBench defines action-conditioned reliability via three levels (physics adherence, action-following fidelity, optimism bias detection) and applies it to 12 model configurations using a 16,000-judgment human corpus,...
-
Matrix-Space Reinforcement Learning for Reusing Local Transition Geometry
MSRL represents trajectory segments as PSD matrices to prove additive composition properties and bootstrap value functions for better transfer, reaching 0.73 AUC versus 0.57-0.65 baselines.
-
JEDI: Joint Embedding Diffusion World Model for Online Model-Based Reinforcement Learning
JEDI is the first online end-to-end latent diffusion world model that trains latents from denoising loss rather than reconstruction, achieving competitive Atari100k results with 43% less VRAM and over 3x faster sampli...
-
Learning Visual Feature-Based World Models via Residual Latent Action
RLA-WM predicts residual latent actions via flow matching to create visual feature world models that outperform prior feature-based and diffusion approaches while enabling offline video-based robot RL.
-
Beyond Test-Time Memory: State-Space Optimal Control for LLM Reasoning
A symplectic LQR layer inserted as an adapter into pretrained LLMs yields large gains on MATH-500, AMC and AIME by solving a latent optimal-control problem at inference time.
-
BiTrajDiff: Bidirectional Trajectory Generation with Diffusion Models for Offline Reinforcement Learning
BiTrajDiff augments offline RL datasets by running independent forward and backward diffusion processes from intermediate states, yielding higher performance than prior one-directional data-augmentation baselines on D4RL.
-
World Action Planner: Generalizable Decision-Making with Action-Conditioned World Models
Pairing VLM-generated action proposals with rollouts from a pose-image-conditioned video world model yields high success rates in novel simulated manipulation tasks without end-to-end policy retraining.
-
Toward Goal-Agnostic Joint-Embedding Predictive Control of Partial Differential Equations
A goal-agnostic latent-dynamics controller for 2D Navier-Stokes improves tracking by planning against a learned kinetic-energy probe rather than raw latent-space distance.
-
DriftWorld: Fast World Modeling through Drifting
An action-conditioned world model trained with drifting generates robot rollout videos in one forward pass, matching diffusion quality while running 2.8-478x faster per-table, and raises GPC-RANK Push-T IoU from 0.635...
-
Solving Markov Decision Processes with Future Information via MPC
Parameterized MPC exactly represents optimal policies for MDPs with future information under identified structural conditions and parameters can be learned via RL.
-
Ada-Diffuser: Latent-Aware Adaptive Diffusion for Decision-Making
Ada-Diffuser is a causal diffusion model that jointly learns observed interaction structure and underlying latent dynamics from minimal observations for adaptive planning and policy learning.
-
TRAP: Tail-aware Ranking Attack for World-Model Planning
TRAP is a tail-aware ranking attack that plants a backdoor in world models so that a trigger causes the model to reorder a few critical imagined trajectories and redirect planning while preserving normal behavior on c...
-
RAY-TOLD: Ray-Based Latent Dynamics for Dense Dynamic Obstacle Avoidance with TDMPC
RAY-TOLD combines ray-based latent dynamics from LiDAR with MPPI control and a learned policy prior via mixture sampling to lower collision rates in high-density dynamic obstacle environments compared to standard MPPI.
-
Cosmos Policy: Fine-Tuning Video Models for Visuomotor Control and Planning
Single-stage fine-tuning of a video model to generate actions as latent frames plus future states and values yields state-of-the-art robot policy performance on LIBERO, RoboCasa, and bimanual tasks.
-
Next-Latent Prediction Transformers Learn Compact World Models
NextLat augments next-token prediction with latent next-state prediction, theoretically converging latents to belief states and showing empirical gains in world modeling, reasoning, planning, and faster inference via ...
-
Next-Latent Prediction Transformers Learn Compact World Models
Adding a next-latent prediction loss to next-token training makes transformer hidden states more predictive of future tokens and improves planning/reasoning on small benchmarks.
-
Ctrl-World: A Controllable Generative World Model for Robot Manipulation
A controllable world model trained on the DROID dataset generates consistent multi-view robot trajectories for over 20 seconds and improves generalist policy success rates by 44.7% via imagined trajectory fine-tuning.
-
Model-Based Reinforcement Learning under Random Observation Delays
A delay-aware model-based RL framework with sequential belief filtering handles random out-of-sequence observations in POMDPs and outperforms MDP baselines while showing robustness to delay shifts.
-
High-Precision and High-Efficiency Trajectory Tracking for Excavators Based on Closed-Loop Dynamics
EfficientTrack integrates model-based learning and closed-loop dynamics to minimize tracking errors in excavator trajectory control with high efficiency and precision, outperforming prior learning-based methods in sim...
-
V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning
V-JEPA 2 pre-trained on massive unlabeled video achieves strong results on motion understanding and action anticipation, SOTA video QA at 8B scale, and enables zero-shot robotic planning on Franka arms using only 62 h...
-
Real-Time Execution of Action Chunking Flow Policies
Real-time chunking (RTC) allows diffusion- and flow-based action chunking policies to execute smoothly and asynchronously, maintaining high success rates on dynamic tasks even with significant inference latency.
-
DINO-WM: World Models on Pre-trained Visual Features enable Zero-shot Planning
DINO-WM builds world models on pre-trained DINOv2 features to enable zero-shot planning from offline data without rewards or demonstrations.
-
Valdi: Value Diffusion World Models
Valdi pairs a latent diffusion dynamics model with end-to-end MPC training and reports that one diffusion step matches an MLP baseline on CarRacing while exposing a multimodality-control trade-off.
-
Scaling World-Model Reinforcement Learning Through Diffusion Policy Optimization
MBDPO reformulates policy optimization as a diffusion process over searched trajectories in latent world models to reduce misalignment between search and value learning.
-
stable-worldmodel: A Platform for Reproducible World Modeling Research and Evaluation
The paper presents stable-worldmodel (swm), a platform with high-performance data layer, modern world model baselines, planning solvers, and extended environments for reproducible research and generalization evaluation.
-
CoRL-MPPI: Enhancing MPPI With Learnable Behaviours For Efficient And Provably-Safe Multi-Robot Collision Avoidance
CoRL-MPPI injects a learned cooperative policy into MPPI's sampling distribution to speed up and make safer multi-robot navigation in dense simulations.
-
D2 Actor Critic: Diffusion Actor Meets Distributional Critic
D2AC combines a diffusion actor with a distributional critic via fused distributional RL and clipped double Q-learning to reach state-of-the-art results on 18 hard control benchmarks including Humanoid, Dog, and Shadow Hand.
-
Self-Predictive Representations for Combinatorial Generalization in Behavioral Cloning
BYOL-γ uses self-predictive representations to approximate successor representations, improving zero-shot combinatorial generalization in goal-conditioned behavioral cloning.
-
InternVideo3: Agentify Foundation Models with Multimodal Contextual Reasoning
InternVideo3 introduces Multimodal Contextual Reasoning and M^2LA attention to enable closed-loop evidence accumulation in long-video understanding and agentic tool use, reporting strong benchmark results.
-
Efficient On-policy Visual-RL via Stochastic Decoupled Policy Gradient
SDPG is a new on-policy visual RL algorithm that estimates gradients via stochastic perturbations of rollouts, achieving faster training and lower memory use than baselines on visual MuJoCo tasks while adding new robo...
-
Reinforcement Learning: From Algorithms To Foundation Models
A dissertation uniting the author's published results: non-exploitable Nash-DQN policies and the FightLadder benchmark for games, plus diffusion/consistency-model world models for RL — a compilation rather than new results.
-
Enhancing Human-Likeness in Reinforcement Learning Agents via Hierarchical Macro Action Quantization
HiMAQ applies hierarchical vector quantization to human demonstrations to generate macro actions that yield higher human-likeness scores than flat MAQ on D4RL while matching or exceeding success rates across IQL, SAC,...
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.