Learning Smooth Time-Varying Linear Policies with an Action Jacobian Penalty

• URL: http://arxiv.org/abs/2602.18312v1
• Date: Fri, 20 Feb 2026 16:11:19 GMT
• Title: Learning Smooth Time-Varying Linear Policies with an Action Jacobian Penalty
• Abstract summary: Reinforcement learning provides a framework for learning control policies that can reproduce diverse motions for simulated characters.<n>Existing work addresses this issue by adding a reward term that penalizes a large change in actions over time.<n>We propose to use the action Jacobian penalty, which penalizes changes in action with respect to the changes in simulated state directly through auto differentiation.
• Score: 1.8122712065585906
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Reinforcement learning provides a framework for learning control policies that can reproduce diverse motions for simulated characters. However, such policies often exploit unnatural high-frequency signals that are unachievable by humans or physical robots, making them poor representations of real-world behaviors. Existing work addresses this issue by adding a reward term that penalizes a large change in actions over time. This term often requires substantial tuning efforts. We propose to use the action Jacobian penalty, which penalizes changes in action with respect to the changes in simulated state directly through auto differentiation. This effectively eliminates unrealistic high-frequency control signals without task specific tuning. While effective, the action Jacobian penalty introduces significant computational overhead when used with traditional fully connected neural network architectures. To mitigate this, we introduce a new architecture called a Linear Policy Net (LPN) that significantly reduces the computational burden for calculating the action Jacobian penalty during training. In addition, a LPN requires no parameter tuning, exhibits faster learning convergence compared to baseline methods, and can be more efficiently queried during inference time compared to a fully connected neural network. We demonstrate that a Linear Policy Net, combined with the action Jacobian penalty, is able to learn policies that generate smooth signals while solving a number of motion imitation tasks with different characteristics, including dynamic motions such as a backflip and various challenging parkour skills. Finally, we apply this approach to create policies for dynamic motions on a physical quadrupedal robot equipped with an arm.

Related papers

• FreqPolicy: Frequency Autoregressive Visuomotor Policy with Continuous Tokens [47.735852718586216]
  We propose a novel paradigm for visuomotor policy learning that progressively models hierarchical frequency components.<n>To further enhance precision, we introduce continuous latent representations that maintain smoothness and continuity in the action space.<n>Our approach outperforms existing methods in both accuracy and efficiency.
  arXiv  Detail & Related papers  (2025-06-02T12:13:51Z)
• Spectral Normalization for Lipschitz-Constrained Policies on Learning Humanoid Locomotion [12.790605143952996]
  This work proposes Spectral Normalization (SN) as an efficient replacement for enforcing Lipschitz continuity.<n> SN effectively limits high-frequency policy fluctuations while significantly reducing GPU memory usage.<n> Experimental evaluations in both simulation and real-world humanoid robot show that SN achieves performance comparable to gradient penalty methods.
  arXiv  Detail & Related papers  (2025-04-11T04:12:15Z)
• Autonomous Vehicle Controllers From End-to-End Differentiable Simulation [57.278726604424556]
  We propose a differentiable simulator and design an analytic policy gradients (APG) approach to training AV controllers.<n>Our proposed framework brings the differentiable simulator into an end-to-end training loop, where gradients of environment dynamics serve as a useful prior to help the agent learn a more grounded policy.<n>We find significant improvements in performance and robustness to noise in the dynamics, as well as overall more intuitive human-like handling.
  arXiv  Detail & Related papers  (2024-09-12T11:50:06Z)
• DiAReL: Reinforcement Learning with Disturbance Awareness for Robust Sim2Real Policy Transfer in Robot Control [0.0]
  Delayed Markov decision processes fulfill the Markov property by augmenting the state space of agents with a finite time window of recently committed actions. We introduce a disturbance-augmented Markov decision process in delayed settings as a novel representation to incorporate disturbance estimation in training on-policy reinforcement learning algorithms.
  arXiv  Detail & Related papers  (2023-06-15T10:11:38Z)
• Latent Exploration for Reinforcement Learning [87.42776741119653]
  In Reinforcement Learning, agents learn policies by exploring and interacting with the environment. We propose LATent TIme-Correlated Exploration (Lattice), a method to inject temporally-correlated noise into the latent state of the policy network.
  arXiv  Detail & Related papers  (2023-05-31T17:40:43Z)
• Developing Driving Strategies Efficiently: A Skill-Based Hierarchical Reinforcement Learning Approach [0.7373617024876725]
  Reinforcement learning is a common tool to model driver policies. We propose skill-based" hierarchical driving strategies, where motion primitives are designed and used as high-level actions.
  arXiv  Detail & Related papers  (2023-02-04T15:09:51Z)
• Dynamics-aware Adversarial Attack of Adaptive Neural Networks [75.50214601278455]
  We investigate the dynamics-aware adversarial attack problem of adaptive neural networks. We propose a Leaded Gradient Method (LGM) and show the significant effects of the lagged gradient. Our LGM achieves impressive adversarial attack performance compared with the dynamic-unaware attack methods.
  arXiv  Detail & Related papers  (2022-10-15T01:32:08Z)
• Accelerated Policy Learning with Parallel Differentiable Simulation [59.665651562534755]
  We present a differentiable simulator and a new policy learning algorithm (SHAC) Our algorithm alleviates problems with local minima through a smooth critic function. We show substantial improvements in sample efficiency and wall-clock time over state-of-the-art RL and differentiable simulation-based algorithms.
  arXiv  Detail & Related papers  (2022-04-14T17:46:26Z)
• Learning Robust Policy against Disturbance in Transition Dynamics via State-Conservative Policy Optimization [63.75188254377202]
  Deep reinforcement learning algorithms can perform poorly in real-world tasks due to discrepancy between source and target environments. We propose a novel model-free actor-critic algorithm to learn robust policies without modeling the disturbance in advance. Experiments in several robot control tasks demonstrate that SCPO learns robust policies against the disturbance in transition dynamics.
  arXiv  Detail & Related papers  (2021-12-20T13:13:05Z)
• Neural Dynamic Policies for End-to-End Sensorimotor Learning [51.24542903398335]
  The current dominant paradigm in sensorimotor control, whether imitation or reinforcement learning, is to train policies directly in raw action spaces. We propose Neural Dynamic Policies (NDPs) that make predictions in trajectory distribution space. NDPs outperform the prior state-of-the-art in terms of either efficiency or performance across several robotic control tasks.
  arXiv  Detail & Related papers  (2020-12-04T18:59:32Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.