Dynamic Deep-reinforcement-learning Algorithm In Partially Observable Markov Decision Processes

Abstract

Recent studies have greatly improved reinforcement learning, and an increased interest in real-world implementation has emerged. In many cases, the implementation is challenged by time-varying disturbances as it introduces hidden states, which makes the problem best described with Partially Observable Markov Decision Processes. An effective approach to address this problem is to introduce a Recurrent Neural Network (RNN) in place of a state estimator. However, only a few studies have investigated the types of information to be supplied to the RNN and the network architecture to handle them. This study discusses the effectiveness of the inclusion of action along with observation and the impact of network architecture to handle them by providing interpretations of how the trajectories are summarized at LSTM networks. Specifically, three novel approaches with different architectures are introduced. All algorithms demonstrated the effectiveness of the inclusion of the action trajectories i

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyomi2023dynamic

Related papers

• On Improving Deep Reinforcement Learning For Pomdps (2017)0.00
• Deep Hierarchical Reinforcement Learning Algorithm In Partially Observable Markov Decision Processes (2018)12.87
• Real-time Recurrent Reinforcement Learning (2023)2.26
• Perception-prediction-reaction Agents For Deep Reinforcement Learning (2020)0.00
• Recurrent Networks, Hidden States And Beliefs In Partially Observable Environments (2022)0.00
• Recurrent Natural Policy Gradient For Pomdps (2024)0.00
• Variational Recurrent Models For Solving Partially Observable Control Tasks (2019)0.00
• Act-then-measure: Reinforcement Learning For Partially Observable Environments With Active Measuring (2023)3.58