DAQN: Deep Auto-encoder and Q-Network

Abstract

The deep reinforcement learning method usually requires a large number of training images and executing actions to obtain sufficient results. When it is extended a real-task in the real environment with an actual robot, the method will be required more training images due to complexities or noises of the input images, and executing a lot of actions on the real robot also becomes a serious problem. Therefore, we propose an extended deep reinforcement learning method that is applied a generative model to initialize the network for reducing the number of training trials. In this paper, we used a deep q-network method as the deep reinforcement learning method and a deep auto-encoder as the generative model. We conducted experiments on three different tasks: a cart-pole game, an atari game, and a real-game with an actual robot. The proposed method trained efficiently on all tasks than the previous method, especially 2.5 times faster on a task with real environment images.

References in corpus (3)

• Continuous control with deep reinforcement learning
• Image Restoration Using Very Deep Convolutional Encoder-Decoder Networks with Symmetric Skip Connections
• Incentivizing Exploration In Reinforcement Learning With Deep Predictive Models

Cited by in corpus (7)

• Internal Model from Observations for Reward Shaping
• Reinforcement Learning with External Knowledge by using Logical Neural Networks
• Neuro-Symbolic Reinforcement Learning with First-Order Logic
• Spatially-weighted Anomaly Detection with Regression Model
• LOA: Logical Optimal Actions for Text-based Interaction Games
• BF++: a language for general-purpose program synthesis
• Exploiting the potential of deep reinforcement learning for classification tasks in high-dimensional and unstructured data