Memory-efficient Reinforcement Learning with Value-based Knowledge Consolidation

• URL: http://arxiv.org/abs/2205.10868v5
• Date: Mon, 10 Apr 2023 18:53:45 GMT
• Title: Memory-efficient Reinforcement Learning with Value-based Knowledge Consolidation
• Authors: Qingfeng Lan, Yangchen Pan, Jun Luo, A. Rupam Mahmood
• Abstract summary: We propose memory-efficient reinforcement learning algorithms based on the deep Q-network algorithm. Our algorithms reduce forgetting and maintain high sample efficiency by consolidating knowledge from the target Q-network to the current Q-network.
• Score: 14.36005088171571
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Artificial neural networks are promising for general function approximation but challenging to train on non-independent or non-identically distributed data due to catastrophic forgetting. The experience replay buffer, a standard component in deep reinforcement learning, is often used to reduce forgetting and improve sample efficiency by storing experiences in a large buffer and using them for training later. However, a large replay buffer results in a heavy memory burden, especially for onboard and edge devices with limited memory capacities. We propose memory-efficient reinforcement learning algorithms based on the deep Q-network algorithm to alleviate this problem. Our algorithms reduce forgetting and maintain high sample efficiency by consolidating knowledge from the target Q-network to the current Q-network. Compared to baseline methods, our algorithms achieve comparable or better performance in both feature-based and image-based tasks while easing the burden of large experience replay buffers.

Related papers

• Efficient Training of Deep Neural Operator Networks via Randomized Sampling [0.0]
  Deep operator network (DeepNet) has demonstrated success in the real-time prediction of complex dynamics across various scientific and engineering applications. We introduce a random sampling technique to be adopted the training of DeepONet, aimed at improving generalization ability of the model, while significantly reducing computational time. Our results indicate that incorporating randomization in the trunk network inputs during training enhances the efficiency and robustness of DeepONet, offering a promising avenue for improving the framework's performance in modeling complex physical systems.
  arXiv  Detail & Related papers  (2024-09-20T07:18:31Z)
• Unrolled denoising networks provably learn optimal Bayesian inference [54.79172096306631]
  We prove the first rigorous learning guarantees for neural networks based on unrolling approximate message passing (AMP) For compressed sensing, we prove that when trained on data drawn from a product prior, the layers of the network converge to the same denoisers used in Bayes AMP.
  arXiv  Detail & Related papers  (2024-09-19T17:56:16Z)
• Deep Q-network using reservoir computing with multi-layered readout [0.0]
  Recurrent neural network (RNN) based reinforcement learning (RL) is used for learning context-dependent tasks. An approach with replay memory introducing reservoir computing has been proposed, which trains an agent without BPTT. This paper shows that the performance of this method improves by using a multi-layered neural network for the readout layer.
  arXiv  Detail & Related papers  (2022-03-03T00:32:55Z)
• Learning Bayesian Sparse Networks with Full Experience Replay for Continual Learning [54.7584721943286]
  Continual Learning (CL) methods aim to enable machine learning models to learn new tasks without catastrophic forgetting of those that have been previously mastered. Existing CL approaches often keep a buffer of previously-seen samples, perform knowledge distillation, or use regularization techniques towards this goal. We propose to only activate and select sparse neurons for learning current and past tasks at any stage.
  arXiv  Detail & Related papers  (2022-02-21T13:25:03Z)
• Memory Replay with Data Compression for Continual Learning [80.95444077825852]
  We propose memory replay with data compression to reduce the storage cost of old training samples. We extensively validate this across several benchmarks of class-incremental learning and in a realistic scenario of object detection for autonomous driving.
  arXiv  Detail & Related papers  (2022-02-14T10:26:23Z)
• Accelerating Deep Learning Classification with Error-controlled Approximate-key Caching [72.50506500576746]
  We propose a novel caching paradigm, that we named approximate-key caching. While approximate cache hits alleviate DL inference workload and increase the system throughput, they however introduce an approximation error. We analytically model our caching system performance for classic LRU and ideal caches, we perform a trace-driven evaluation of the expected performance, and we compare the benefits of our proposed approach with the state-of-the-art similarity caching.
  arXiv  Detail & Related papers  (2021-12-13T13:49:11Z)
• Group Fisher Pruning for Practical Network Compression [58.25776612812883]
  We present a general channel pruning approach that can be applied to various complicated structures. We derive a unified metric based on Fisher information to evaluate the importance of a single channel and coupled channels. Our method can be used to prune any structures including those with coupled channels.
  arXiv  Detail & Related papers  (2021-08-02T08:21:44Z)
• Improving Computational Efficiency in Visual Reinforcement Learning via Stored Embeddings [89.63764845984076]
  We present Stored Embeddings for Efficient Reinforcement Learning (SEER) SEER is a simple modification of existing off-policy deep reinforcement learning methods. We show that SEER does not degrade the performance of RLizable agents while significantly saving computation and memory.
  arXiv  Detail & Related papers  (2021-03-04T08:14:10Z)
• Reinforcement Learning Based Cooperative Coded Caching under Dynamic Popularities in Ultra-Dense Networks [38.44125997148742]
  caching strategy at small base stations (SBSs) is critical to meet massive high data rate requests. We exploit reinforcement learning (RL) to design a cooperative caching strategy with maximum-distance separable (MDS) coding.
  arXiv  Detail & Related papers  (2020-03-08T10:45:45Z)

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.