mlsanityData to 14 Oct 2026

Deep Incremental Model Informed Reinforcement Learning for Continuous Robotic Control

arXiv 2403.01529 ↗First posted 3 Mar 2024cs.RO cs.SY eess.SYcited by 0

On the map: Deep reinforcement learning methods → RL for robot locomotion and manipulation

Abstract (arXiv)

Model-based reinforcement learning attempts to use an available or learned model to improve the data efficiency of reinforcement learning. This work proposes a one-step lookback approach that jointly learns the deep incremental model and the policy to realize the sample-efficient continuous robotic control, wherein the control-theoretical knowledge is utilized to decrease the model learning difficulty and facilitate efficient training. Specifically, we use one-step backward data to facilitate the deep incremental model, an alternative structured representation of the robotic evolution model, that accurately predicts the robotic movement but with low sample complexity. This is because the formulated deep incremental model degrades the model learning difficulty into a parametric matrix learning problem, which is especially favourable to high-dimensional robotic applications. The imagined data from the learned deep incremental model is used to supplement training data to enhance the sample efficiency. Comparative numerical simulations on benchmark continuous robotics control problems are conducted to validate the efficiency of our proposed one-step lookback approach.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RL for robot locomotion and manipulation, one of 15 directions in Deep reinforcement learning methods. Builds on 7 of its 11 references that are in the map. First posted on arXiv 3 Mar 2024.

Builds on

7 of 11 references.

References · 7

  1. 2018Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Modelscited by 774
  2. 2019When to Trust Your Model: Model-Based Policy Optimizationcited by 773
  3. 2017Neural Network Dynamics for Model-Based Deep Reinforcement Learning with Model-Free Fine-Tuningcited by 297
  4. 2019Benchmarking Model-Based Reinforcement Learningcited by 162
  5. 2015Gaussian Processes for Data-Efficient Learning in Robotics and Controlcited by 98
  6. 2015Learning Contact-Rich Manipulation Skills with Guided Policy Searchcited by 38
  7. 2021Mismatched No More: Joint Model-Policy Optimization for Model-Based RLcited by 36

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Deep Policy Gradient Methods Without Batch Updates, Target Networks, or Replay Buffers
  2. 2025Robotic World Model: A Neural Network Simulator for Robust Policy Optimization in Robotics
  3. 2025Efficient Model-Based Reinforcement Learning for Robot Control via Online Optimization
  4. 2026Self-adapting Robotic Agents through Online Continual Reinforcement Learning with World Model Feedback
  5. 2024An Efficient Model-Based Approach on Learning Agile Motor Skills without Reinforcement
  6. 2025Taxonomy and Trends in Reinforcement Learning for Robotics and Control Systems: A Structured Review
  7. 2026Efficient Reinforcement Learning using Linear Koopman Dynamics for Nonlinear Robotic Systems
  8. 2025Accelerating Model-Based Reinforcement Learning with State-Space World Models