mlsanityData to 14 Oct 2026

QMDP-Net: Deep Learning for Planning under Partial Observability

arXiv 1703.06692 ↗First posted 20 Mar 2017cs.AI cs.LG cs.NEcited by 51

Not on the map. Why?

Abstract (arXiv)

This paper introduces the QMDP-net, a neural network architecture for planning under partial observability. The QMDP-net combines the strengths of model-free learning and model-based planning. It is a recurrent policy network, but it represents a policy for a parameterized set of tasks by connecting a model with a planning algorithm that solves the model, thus embedding the solution structure of planning in a network learning architecture. The QMDP-net is fully differentiable and allows for end-to-end training. We train a QMDP-net on different tasks so that it can generalize to new ones in the parameterized task set and "transfer" to other similar tasks beyond the set. In preliminary experiments, QMDP-net showed strong performance on several robotic tasks in simulation. Interestingly, while QMDP-net encodes the QMDP algorithm, it sometimes outperforms the QMDP algorithm in the experiments, as a result of end-to-end learning.

Key facts. Cited by 51 papers in the map (data through 14 Oct 2026). First posted on arXiv 20 Mar 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 14; 2022: 14; 2023: 7; 2024: 5; 2025: 5; 2026: 6.

51 papers.

Sort:

By area:

  1. 2021Federated Reinforcement Learning: Techniques, Applications, and Open Challengescited by 81
  2. 2022TASKOGRAPHY: Evaluating robot task planning over large 3D scene graphscited by 59
  3. 2023Safe Reinforcement Learning via Probabilistic Logic Shieldscited by 42
  4. 2022DiffStack: A Differentiable and Modular Control Stack for Autonomous Vehiclescited by 37
  5. 2021Differentiable SLAM-net: Learning Particle SLAM for Visual Navigationcited by 34
  6. 2021NeRP: Neural Rearrangement Planning for Unknown Objectscited by 34
  7. 2021INVIGORATE: Interactive Visual Grounding and Grasping in Cluttercited by 32
  8. 2021Differentiable Spatial Planning using Transformerscited by 25
  9. 2021Structured World Belief for Reinforcement Learning in POMDPcited by 21
  10. 2023Factor Graph Neural Networkscited by 15
  11. 2021Cut the CARP: Fishing for zero-shot story evaluationcited by 14
  12. 2021Closing the Planning-Learning Loop with Application to Autonomous Drivingcited by 12
38 more
  1. 2022Recurrent networks, hidden states and beliefs in partially observable environmentscited by 12
  2. 2021Theory of Mind for Deep Reinforcement Learning in Hanabicited by 11
  3. 2022Learning to Optimize in Model Predictive Controlcited by 11
  4. 2022Learning Sampling Distributions for Model Predictive Controlcited by 10
  5. 2023A Unified View on Solving Objective Mismatch in Model-Based Reinforcement Learningcited by 9
  6. 2021Compositional Learning-based Planning for Vision POMDPscited by 8
  7. 2022Group Distributionally Robust Reinforcement Learning with Hierarchical Latent Variablescited by 7
  8. 2022Winning the CityLearn Challenge: Adaptive Optimization with Evolutionary Search under Trajectory-based Guidancecited by 7
  9. 2022Learning Graph Search Heuristicscited by 7
  10. 2023Deep Model Predictive Optimizationcited by 7
  11. 2022Integrating Symmetry into Differentiable Planning with Steerable Convolutionscited by 6
  12. 2022Scaling up and Stabilizing Differentiable Planning with Implicit Differentiationcited by 6
  13. 2024Learning Online Belief Prediction for Efficient POMDP Planning in Autonomous Drivingcited by 5
  14. 2024Imagine, Initialize, and Explore: An Effective Exploration Method in Multi-Agent Reinforcement Learningcited by 5
  15. 2024Versatile Navigation under Partial Observability via Value-guided Diffusion Policycited by 5
  16. 2021Safe Deep Q-Network for Autonomous Vehicles at Unsignalized Intersectioncited by 4
  17. 2021Towards real-world navigation with deep differentiable plannerscited by 4
  18. 2022Data-driven End-to-end Learning of Pole Placement Control for Nonlinear Dynamics via Koopman Invariant Subspacescited by 3
  19. 2024Episodic Reinforcement Learning with Expanded State-reward Spacecited by 3
  20. 2026UWM-JEPA: Predictive World Models That Imagine in Belief Spacecited by 3
  21. 2021Active Inference Tree Search in Large POMDPscited by 2
  22. 2022Reward Function Optimization of a Deep Reinforcement Learning Collision Avoidance Systemcited by 2
  23. 2023Learning An Active Inference Model of Driver Perception and Control: Application to Vehicle Car-Followingcited by 2
  24. 2023Simplifying Complex Observation Models in Continuous POMDP Planning with Probabilistic Guarantees and Practicecited by 2
  25. 2025Deep Belief Markov Models for POMDP Inferencecited by 2
  26. 2021Differentiable Robust LQR Layerscited by 1
  27. 2022Private Multiparty Perception for Navigationcited by 1
  28. 2025Belief States for Cooperative Multi-Agent Reinforcement Learning under Partial Observabilitycited by 1
  29. 2022Task Allocation with Load Management in Multi-Agent Teamscited by 0
  30. 2023Fast exploration and learning of latent graphs with aliased observationscited by 0
  31. 2024Approximate Control for Continuous-Time POMDPscited by 0
  32. 2025ToMCAT: Theory-of-Mind for Cooperative Agents in Teams via Multiagent Diffusion Policiescited by 0
  33. 2025Neural Value Iterationcited by 0
  34. 2025POrTAL: Plan-Orchestrated Tree Assembly for Lookaheadcited by 0
  35. 2026Emergence of a Flow-Assisted Casting Strategy for Olfactory Navigation via Memory-Augmented Reinforcement Learningcited by 0
  36. 2026Differentiable Belief-based Opponent Shapingcited by 0
  37. 2026Generative-Model Predictive Planning for Navigation in Partially Observable Environmentscited by 0
  38. 2026VOiLA: Vectorized Online Planning with Learned Diffusion Models for POMDP Agentscited by 0

50 most cited of 51 All 51 (JSON)