Backpropagating Through Simulation: Analytic Policy Gradients for Sample and Learning Efficient Differentiable Continuous Control

• URL: http://arxiv.org/abs/2606.21525v1
• Date: Fri, 19 Jun 2026 15:22:51 GMT
• Title: Backpropagating Through Simulation: Analytic Policy Gradients for Sample and Learning Efficient Differentiable Continuous Control
• Abstract summary: Analytic Policy Gradients (APG) and PPO are evaluated against PPO on four continuous control tasks of increasing dynamical complexity.<n>We report a segmented backpropagation scheme with MC and critic-based bootstrap modes that mitigates gradient degradation on long-horizon tasks.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Model-free reinforcement learning algorithms such as Proximal Policy Optimization (PPO) treat the environment as a black box, estimating policy gradients from sampled rewards; this process demands millions of interactions and relies on high-variance advantage estimates. When environment dynamics are differentiable, the return is an end-to-end differentiable function of the policy parameters, enabling exact gradient computation via backpropagation through simulation. We term this approach Analytic Policy Gradients (APG) and evaluate it against PPO on four continuous control tasks of increasing dynamical complexity: a one-dimensional point-mass target-reaching task, a 2D point-mass navigation task with obstacle avoidance, a 2D rigid-body T-block pushing task, and a 7-DOF Franka FR3 end-effector reaching task. Both algorithms share identical model architectures, observation normalization, and optimizer settings. To decouple sample efficiency from compute efficiency, we design a multi-axis evaluation protocol that records performance against environment steps and gradient steps. We report a segmented backpropagation scheme with MC and critic-based bootstrap modes that mitigates gradient degradation on long-horizon tasks, and present ablations over segment length and bootstrap strategy.

Related papers

• Path Integral Value Matching for Linear Quadratic Stochastic Optimal Control [26.034302137738127]
  Current state-of-the-art policy-based methods suffer from prohibitive computational costs and instability.<n>We propose a paradigm shift toward a value-based approach by revisiting Path Integral Control (PIC)<n>Building upon this theoretical foundation, we propose the Path Integral Value Matching (PI-VM) algorithm.
  arXiv  Detail & Related papers  (2026-08-11T10:29:49Z)
• IADD-TR: Intervention-Aware Dynamics Decoupling with Targeted Regularization for Model-Based Reinforcement Learning [57.16513298507272]
  We propose IADD-TR, a unified framework combining Intervention-Aware Dynamics Decoupling (IADD) and Targeted Regularization (TR)<n>IADD factorizes transitions into an action-intervention stage and an action-free natural evolution stage, using a zero-action anchor to resolve the non-uniqueness of this two-stage factorization for robust generalization.<n>For policy learning, we derive TR from the efficient influence function of a replay-state policy-gradient functional.
  arXiv  Detail & Related papers  (2026-08-11T08:20:02Z)
• Actor-Critic with Active Importance Sampling [61.41272490044518]
  This paper introduces the Active-Importance-Sampling Actor-Critic (AISAC) algorithm.<n>AISAC is an extension of the Actor-Critic framework for reducing variance in policy gradient estimation.<n> Experiments show improved learning speed, sample efficiency, and training compared to standard Actor-Critic methods.
  arXiv  Detail & Related papers  (2026-05-08T01:21:32Z)
• Relative Entropy Pathwise Policy Optimization [66.03329137921949]
  We present an on-policy algorithm that trains Q-value models purely from on-policy trajectories.<n>We show how to combine policies for exploration with constrained updates for stable training, and evaluate important architectural components that stabilize value function learning.
  arXiv  Detail & Related papers  (2025-07-15T06:24:07Z)
• Learning Optimal Deterministic Policies with Stochastic Policy Gradients [62.81324245896716]
  Policy gradient (PG) methods are successful approaches to deal with continuous reinforcement learning (RL) problems. In common practice, convergence (hyper)policies are learned only to deploy their deterministic version. We show how to tune the exploration level used for learning to optimize the trade-off between the sample complexity and the performance of the deployed deterministic policy.
  arXiv  Detail & Related papers  (2024-05-03T16:45:15Z)
• Stabilizing Policy Gradients for Stochastic Differential Equations via Consistency with Perturbation Process [11.01014302314467]
  We focus on optimizing deep neural networks parameterized differential equations (SDEs) We propose constraining the SDE to be consistent with its associated perturbation process. Our framework offers a versatile selection of policy gradient methods to effectively and efficiently train SDEs.
  arXiv  Detail & Related papers  (2024-03-07T02:24:45Z)
• Gradient Informed Proximal Policy Optimization [35.22712034665224]
  We introduce a novel policy learning method that integrates analytical gradients from differentiable environments with the Proximal Policy Optimization (PPO) algorithm. By adaptively modifying the alpha value, we can effectively manage the influence of analytical policy gradients during learning. Our proposed approach outperforms baseline algorithms in various scenarios, such as function optimization, physics simulations, and traffic control environments.
  arXiv  Detail & Related papers  (2023-12-14T07:50:21Z)
• Multi-Objective Policy Gradients with Topological Constraints [108.10241442630289]
  We present a new algorithm for a policy gradient in TMDPs by a simple extension of the proximal policy optimization (PPO) algorithm. We demonstrate this on a real-world multiple-objective navigation problem with an arbitrary ordering of objectives both in simulation and on a real robot.
  arXiv  Detail & Related papers  (2022-09-15T07:22:58Z)
• Jointly Learning Environments and Control Policies with Projected Stochastic Gradient Ascent [3.118384520557952]
  We introduce a deep reinforcement learning algorithm combining policy gradient methods with model-based optimization techniques to solve this problem. In essence, our algorithm iteratively approximates the gradient of the expected return via Monte-Carlo sampling and automatic differentiation. We show that DEPS performs at least as well or better in all three environments, consistently yielding solutions with higher returns in fewer iterations.
  arXiv  Detail & Related papers  (2020-06-02T16:08:07Z)
• Discrete Action On-Policy Learning with Action-Value Critic [72.20609919995086]
  Reinforcement learning (RL) in discrete action space is ubiquitous in real-world applications, but its complexity grows exponentially with the action-space dimension. We construct a critic to estimate action-value functions, apply it on correlated actions, and combine these critic estimated action values to control the variance of gradient estimation. These efforts result in a new discrete action on-policy RL algorithm that empirically outperforms related on-policy algorithms relying on variance control techniques.
  arXiv  Detail & Related papers  (2020-02-10T04:23:09Z)

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.