Reward Shaping Using Convolutional Neural Network

• URL: http://arxiv.org/abs/2210.16956v1
• Date: Sun, 30 Oct 2022 21:28:22 GMT
• Title: Reward Shaping Using Convolutional Neural Network
• Authors: Hani Sami, Hadi Otrok, Jamal Bentahar, Azzam Mourad, Ernesto Damiani
• Abstract summary: We propose a potential-based reward shaping mechanism using Convolutional Neural Network (CNN) The proposed VIN-RS embeds a CNN trained on computed labels using the message passing mechanism of the Hidden Markov Model. Our results illustrate promising improvements in the learning speed and maximum cumulative reward compared to the state-of-the-art.
• Score: 13.098264947461432
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In this paper, we propose Value Iteration Network for Reward Shaping (VIN-RS), a potential-based reward shaping mechanism using Convolutional Neural Network (CNN). The proposed VIN-RS embeds a CNN trained on computed labels using the message passing mechanism of the Hidden Markov Model. The CNN processes images or graphs of the environment to predict the shaping values. Recent work on reward shaping still has limitations towards training on a representation of the Markov Decision Process (MDP) and building an estimate of the transition matrix. The advantage of VIN-RS is to construct an effective potential function from an estimated MDP while automatically inferring the environment transition matrix. The proposed VIN-RS estimates the transition matrix through a self-learned convolution filter while extracting environment details from the input frames or sampled graphs. Due to (1) the previous success of using message passing for reward shaping; and (2) the CNN planning behavior, we use these messages to train the CNN of VIN-RS. Experiments are performed on tabular games, Atari 2600 and MuJoCo, for discrete and continuous action space. Our results illustrate promising improvements in the learning speed and maximum cumulative reward compared to the state-of-the-art.

Related papers

• Multi-Grid Graph Neural Networks with Self-Attention for Computational Mechanics [0.0]
  This paper introduces a novel model merging Self-Attention with Message Passing in GNNs. A dynamic mesh pruning technique based on Self-Attention is proposed, that leads to a robust GNN-based multigrid approach. A new self-supervised training method based on BERT is presented, resulting in a 25% RMSE reduction.
  arXiv  Detail & Related papers  (2024-09-18T11:47:48Z)
• Convolutional Neural Network Compression via Dynamic Parameter Rank Pruning [4.7027290803102675]
  We propose an efficient training method for CNN compression via dynamic parameter rank pruning. Our experiments show that the proposed method can yield substantial storage savings while maintaining or even enhancing classification performance.
  arXiv  Detail & Related papers  (2024-01-15T23:52:35Z)
• PICNN: A Pathway towards Interpretable Convolutional Neural Networks [12.31424771480963]
  We introduce a novel pathway to alleviate the entanglement between filters and image classes. We use the Bernoulli sampling to generate the filter-cluster assignment matrix from a learnable filter-class correspondence matrix. We evaluate the effectiveness of our method on ten widely used network architectures.
  arXiv  Detail & Related papers  (2023-12-19T11:36:03Z)
• Intelligence Processing Units Accelerate Neuromorphic Learning [52.952192990802345]
  Spiking neural networks (SNNs) have achieved orders of magnitude improvement in terms of energy consumption and latency. We present an IPU-optimized release of our custom SNN Python package, snnTorch.
  arXiv  Detail & Related papers  (2022-11-19T15:44:08Z)
• Dynamic Graph Message Passing Networks for Visual Recognition [112.49513303433606]
  Modelling long-range dependencies is critical for scene understanding tasks in computer vision. A fully-connected graph is beneficial for such modelling, but its computational overhead is prohibitive. We propose a dynamic graph message passing network, that significantly reduces the computational complexity.
  arXiv  Detail & Related papers  (2022-09-20T14:41:37Z)
• Invertible Neural Networks for Graph Prediction [22.140275054568985]
  In this work, we address conditional generation using deep invertible neural networks. We adopt an end-to-end training approach since our objective is to address prediction and generation in the forward and backward processes at once.
  arXiv  Detail & Related papers  (2022-06-02T17:28:33Z)
• Pretraining Graph Neural Networks for few-shot Analog Circuit Modeling and Design [68.1682448368636]
  We present a supervised pretraining approach to learn circuit representations that can be adapted to new unseen topologies or unseen prediction tasks. To cope with the variable topological structure of different circuits we describe each circuit as a graph and use graph neural networks (GNNs) to learn node embeddings. We show that pretraining GNNs on prediction of output node voltages can encourage learning representations that can be adapted to new unseen topologies or prediction of new circuit level properties.
  arXiv  Detail & Related papers  (2022-03-29T21:18:47Z)
• Neural Capacitance: A New Perspective of Neural Network Selection via Edge Dynamics [85.31710759801705]
  Current practice requires expensive computational costs in model training for performance prediction. We propose a novel framework for neural network selection by analyzing the governing dynamics over synaptic connections (edges) during training. Our framework is built on the fact that back-propagation during neural network training is equivalent to the dynamical evolution of synaptic connections.
  arXiv  Detail & Related papers  (2022-01-11T20:53:15Z)
• Curriculum By Smoothing [52.08553521577014]
  Convolutional Neural Networks (CNNs) have shown impressive performance in computer vision tasks such as image classification, detection, and segmentation. We propose an elegant curriculum based scheme that smoothes the feature embedding of a CNN using anti-aliasing or low-pass filters. As the amount of information in the feature maps increases during training, the network is able to progressively learn better representations of the data.
  arXiv  Detail & Related papers  (2020-03-03T07:27:44Z)
• Computational optimization of convolutional neural networks using separated filters architecture [69.73393478582027]
  We consider a convolutional neural network transformation that reduces computation complexity and thus speedups neural network processing. Use of convolutional neural networks (CNN) is the standard approach to image recognition despite the fact they can be too computationally demanding.
  arXiv  Detail & Related papers  (2020-02-18T17:42:13Z)
• CNNTOP: a CNN-based Trajectory Owner Prediction Method [1.3793594968500604]
  Trajectory owner prediction is the basis for many applications such as personalized recommendation, urban planning. Existing methods mainly employ RNNs to model trajectories semantically. We propose a CNN-based Trajectory Owner Prediction (CNNTOP) method.
  arXiv  Detail & Related papers  (2020-01-05T07:58:28Z)

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.