ABPT: Amended Backpropagation through Time with Partially Differentiable Rewards

• URL: http://arxiv.org/abs/2501.14513v2
• Date: Wed, 21 May 2025 11:27:06 GMT
• Title: ABPT: Amended Backpropagation through Time with Partially Differentiable Rewards
• Authors: Fanxing Li, Fangyu Sun, Tianbao Zhang, Danping Zou,
• Abstract summary: Quadrotor control policies can be trained with high performance using the exact gradients of the rewards.<n> Partially differentiable rewards will result in biased gradient propagation that degrades training performance.<n>We propose an approach that mitigates gradient bias while preserving the training efficiency of BPTT.
• Score: 3.1986315488647588
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Quadrotor control policies can be trained with high performance using the exact gradients of the rewards to directly optimize policy parameters via backpropagation-through-time (BPTT). However, designing a fully differentiable reward architecture is often challenging. Partially differentiable rewards will result in biased gradient propagation that degrades training performance. To overcome this limitation, we propose Amended Backpropagation-through-Time (ABPT), a novel approach that mitigates gradient bias while preserving the training efficiency of BPTT. ABPT combines 0-step and N-step returns, effectively reducing the bias by leveraging value gradients from the learned Q-value function. Additionally, it adopts entropy regularization and state initialization mechanisms to encourage exploration during training. We evaluate ABPT on four representative quadrotor flight tasks \li{in both real world and simulation}. Experimental results demonstrate that ABPT converges significantly faster and achieves higher ultimate rewards than existing learning algorithms, particularly in tasks involving partially differentiable rewards. The code will be released at http://github.com/Fanxing-LI/ABPT.

Related papers

• Relative Entropy Pathwise Policy Optimization [56.86405621176669]
  We show how to construct a value-gradient driven, on-policy algorithm that allow training Q-value models purely from on-policy data.<n>We propose Relative Entropy Pathwise Policy Optimization (REPPO), an efficient on-policy algorithm that combines the sample-efficiency of pathwise policy gradients with the simplicity and minimal memory footprint of standard on-policy learning.
  arXiv  Detail & Related papers  (2025-07-15T06:24:07Z)
• Fast Training of Recurrent Neural Networks with Stationary State Feedbacks [48.22082789438538]
  Recurrent neural networks (RNNs) have recently demonstrated strong performance and faster inference than Transformers. We propose a novel method that replaces BPTT with a fixed gradient feedback mechanism.
  arXiv  Detail & Related papers  (2025-03-29T14:45:52Z)
• SALE-Based Offline Reinforcement Learning with Ensemble Q-Networks [0.0]
  We propose a model-free actor-critic algorithm that integrates ensemble Q-networks and a gradient diversity penalty from EDAC.<n>Our algorithm achieves higher convergence speed, stability, and performance compared to existing methods.
  arXiv  Detail & Related papers  (2025-01-07T10:22:30Z)
• Efficient Preference-based Reinforcement Learning via Aligned Experience Estimation [37.36913210031282]
  Preference-based reinforcement learning (PbRL) has shown impressive capabilities in training agents without reward engineering. We propose SEER, an efficient PbRL method that integrates label smoothing and policy regularization techniques.
  arXiv  Detail & Related papers  (2024-05-29T01:49:20Z)
• Stabilizing Backpropagation Through Time to Learn Complex Physics [21.850601375335074]
  In physics simulations, backpropagating feedback is crucial to acquiring temporally coherent behavior. The alternative vector field we propose follows from two principles: physics simulators have a balanced gradient flow, and certain modifications to the backpropagation pass leave the positions of the original minima unchanged. Our final procedure is easily implementable via a sequence of gradient stopping and component-wise comparison operations.
  arXiv  Detail & Related papers  (2024-05-03T12:20:08Z)
• Fast and Unified Path Gradient Estimators for Normalizing Flows [5.64979077798699]
  path gradient estimators for normalizing flows have lower variance compared to standard estimators for variational inference. We propose a fast path gradient estimator which improves computational efficiency significantly. We empirically establish its superior performance and reduced variance for several natural sciences applications.
  arXiv  Detail & Related papers  (2024-03-23T16:21:22Z)
• Directly Attention Loss Adjusted Prioritized Experience Replay [0.07366405857677226]
  Prioritized Replay Experience (PER) enables the model to learn more about relatively important samples by artificially changing their accessed frequencies. DALAP is proposed, which can directly quantify the changed extent of the shifted distribution through Parallel Self-Attention network.
  arXiv  Detail & Related papers  (2023-11-24T10:14:05Z)
• Layer-wise Feedback Propagation [53.00944147633484]
  We present Layer-wise Feedback Propagation (LFP), a novel training approach for neural-network-like predictors. LFP assigns rewards to individual connections based on their respective contributions to solving a given task. We demonstrate its effectiveness in achieving comparable performance to gradient descent on various models and datasets.
  arXiv  Detail & Related papers  (2023-08-23T10:48:28Z)
• Reward Imputation with Sketching for Contextual Batched Bandits [48.80803376405073]
  Contextual batched bandit (CBB) is a setting where a batch of rewards is observed from the environment at the end of each episode. Existing approaches for CBB often ignore the rewards of the non-executed actions, leading to underutilization of feedback information. We propose Sketched Policy Updating with Imputed Rewards (SPUIR) that completes the unobserved rewards using sketching.
  arXiv  Detail & Related papers  (2022-10-13T04:26:06Z)
• Sample-Efficient Optimisation with Probabilistic Transformer Surrogates [66.98962321504085]
  This paper investigates the feasibility of employing state-of-the-art probabilistic transformers in Bayesian optimisation. We observe two drawbacks stemming from their training procedure and loss definition, hindering their direct deployment as proxies in black-box optimisation. We introduce two components: 1) a BO-tailored training prior supporting non-uniformly distributed points, and 2) a novel approximate posterior regulariser trading-off accuracy and input sensitivity to filter favourable stationary points for improved predictive performance.
  arXiv  Detail & Related papers  (2022-05-27T11:13:17Z)
• Dynamics-Aware Comparison of Learned Reward Functions [21.159457412742356]
  The ability to learn reward functions plays an important role in enabling the deployment of intelligent agents in the real world. Reward functions are typically compared by considering the behavior of optimized policies, but this approach conflates deficiencies in the reward function with those of the policy search algorithm used to optimize it. We propose the Dynamics-Aware Reward Distance (DARD), a new reward pseudometric.
  arXiv  Detail & Related papers  (2022-01-25T03:48:00Z)
• Robust and Adaptive Temporal-Difference Learning Using An Ensemble of Gaussian Processes [70.80716221080118]
  The paper takes a generative perspective on policy evaluation via temporal-difference (TD) learning. The OS-GPTD approach is developed to estimate the value function for a given policy by observing a sequence of state-reward pairs. To alleviate the limited expressiveness associated with a single fixed kernel, a weighted ensemble (E) of GP priors is employed to yield an alternative scheme.
  arXiv  Detail & Related papers  (2021-12-01T23:15:09Z)
• Back to Basics: Efficient Network Compression via IMP [22.586474627159287]
  Iterative Magnitude Pruning (IMP) is one of the most established approaches for network pruning. IMP is often argued that it reaches suboptimal states by not incorporating sparsification into the training phase. We find that IMP with SLR for retraining can outperform state-of-the-art pruning-during-training approaches.
  arXiv  Detail & Related papers  (2021-11-01T11:23:44Z)
• Adapting Stepsizes by Momentumized Gradients Improves Optimization and Generalization [89.66571637204012]
  textscAdaMomentum on vision, and achieves state-the-art results consistently on other tasks including language processing. textscAdaMomentum on vision, and achieves state-the-art results consistently on other tasks including language processing. textscAdaMomentum on vision, and achieves state-the-art results consistently on other tasks including language processing.
  arXiv  Detail & Related papers  (2021-06-22T03:13:23Z)
• Correcting Momentum in Temporal Difference Learning [95.62766731469671]
  We argue that momentum in Temporal Difference (TD) learning accumulates gradients that become doubly stale. We show that this phenomenon exists, and then propose a first-order correction term to momentum. An important insight of this work is that deep RL methods are not always best served by directly importing techniques from the supervised setting.
  arXiv  Detail & Related papers  (2021-06-07T20:41:15Z)
• Experience Replay with Likelihood-free Importance Weights [123.52005591531194]
  We propose to reweight experiences based on their likelihood under the stationary distribution of the current policy. We apply the proposed approach empirically on two competitive methods, Soft Actor Critic (SAC) and Twin Delayed Deep Deterministic policy gradient (TD3)
  arXiv  Detail & Related papers  (2020-06-23T17:17:44Z)
• Extrapolation for Large-batch Training in Deep Learning [72.61259487233214]
  We show that a host of variations can be covered in a unified framework that we propose. We prove the convergence of this novel scheme and rigorously evaluate its empirical performance on ResNet, LSTM, and Transformer.
  arXiv  Detail & Related papers  (2020-06-10T08:22:41Z)
• The Break-Even Point on Optimization Trajectories of Deep Neural Networks [64.7563588124004]
  We argue for the existence of the "break-even" point on this trajectory. We show that using a large learning rate in the initial phase of training reduces the variance of the gradient. We also show that using a low learning rate results in bad conditioning of the loss surface even for a neural network with batch normalization layers.
  arXiv  Detail & Related papers  (2020-02-21T22:55:51Z)

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.