VMAV-C: A Deep Attention-based Reinforcement Learning Algorithm For Model-based Control

Abstract

Recent breakthroughs in Go play and strategic games have witnessed the great potential of reinforcement learning in intelligently scheduling in uncertain environment, but some bottlenecks are also encountered when we generalize this paradigm to universal complex tasks. Among them, the low efficiency of data utilization in model-free reinforcement algorithms is of great concern. In contrast, the model-based reinforcement learning algorithms can reveal underlying dynamics in learning environments and seldom suffer the data utilization problem. To address the problem, a model-based reinforcement learning algorithm with attention mechanism embedded is proposed as an extension of World Models in this paper. We learn the environment model through Mixture Density Network Recurrent Network(MDN-RNN) for agents to interact, with combinations of variational auto-encoder(VAE) and attention incorporated in state value estimates during the process of learning policy. In this way, agent can learn opt

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyliang2018vmav

Related papers

• Towards Model-based Reinforcement Learning For Industry-near Environments (2019)5.84
• Sa-matd3:self-attention-based Multi-agent Continuous Control Method In Cooperative Environments (2021)11.76
• Continual Visual Reinforcement Learning With A Life-long World Model (2023)2.26
• Drama: Mamba-enabled Model-based Reinforcement Learning Is Sample And Parameter Efficient (2024)0.00
• MABL: Bi-level Latent-variable World Model For Sample-efficient Multi-agent Reinforcement Learning (2023)0.00
• Towards A Simple Approach To Multi-step Model-based Reinforcement Learning (2018)0.00
• Reinforcement Learning With World Model (2019)0.00
• On The Model-based Stochastic Value Gradient For Continuous Reinforcement Learning (2020)0.00