An Adaptive Synchronization Approach For Weights Of Deep Reinforcement Learning

Abstract

Deep Q-Networks (DQN) is one of the most well-known methods of deep reinforcement learning, which uses deep learning to approximate the action-value function. Solving numerous Deep reinforcement learning challenges such as moving targets problem and the correlation between samples are the main advantages of this model. Although there have been various extensions of DQN in recent years, they all use a similar method to DQN to overcome the problem of moving targets. Despite the advantages mentioned, synchronizing the network weight in a fixed step size, independent of the agent's behavior, may in some cases cause the loss of some properly learned networks. These lost networks may lead to states with more rewards, hence better samples stored in the replay memory for future training. In this paper, we address this problem from the DQN family and provide an adaptive approach for the synchronization of the neural weights used in DQN. In this method, the synchronization of weights is done bas

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keybadran2020an

Related papers

• M\(^2\)DQN: A Robust Method For Accelerating Deep Q-learning Network (2022)0.00
• Enhancing Q-value Updates In Deep Q-learning Via Successor-state Prediction (2025)0.00
• Deep Q-networks For Accelerating The Training Of Deep Neural Networks (2016)0.00
• Weighted Double Deep Multiagent Reinforcement Learning In Stochastic Cooperative Environments (2018)0.00
• A Theoretical Analysis Of Deep Q-learning (2019)0.00
• Elastic Step DQN: A Novel Multi-step Algorithm To Alleviate Overestimation In Deep Qnetworks (2022)10.85
• Deep Reinforcement Learning With Weighted Q-learning (2020)0.00
• Adaptive \(q\)-network: On-the-fly Target Selection For Deep Reinforcement Learning (2024)0.00