Performance Enhancement of Deep Reinforcement Learning Networks Using Feature Extraction

  title={Performance Enhancement of Deep Reinforcement Learning Networks Using Feature Extraction},
  author={Joaquin Ollero and Christopher Child},
The combination of Deep Learning and Reinforcement Learning, termed Deep Reinforcement Learning Networks (DRLN), offers the possibility of using a Deep Learning Neural Network to produce an approximate Reinforcement Learning value table that allows extraction of features from neurons in the hidden layers of the network. This paper presents a two stage technique for training a DRLN on features extracted from a DRLN trained on a identical problem, via the implementation of the Q-Learning… 


  • Udc
  • Computer Science
  • 2021
Improved reinforcement learning parameters on the example of the “Water World” problem were improved by increasing the accuracy of the model of the physical process represented by a deep neural network.



Dueling Network Architectures for Deep Reinforcement Learning

This paper presents a new neural network architecture for model-free reinforcement learning that leads to better policy evaluation in the presence of many similar-valued actions and enables the RL agent to outperform the state-of-the-art on the Atari 2600 domain.

Understanding the difficulty of training deep feedforward neural networks

The objective here is to understand better why standard gradient descent from random initialization is doing so poorly with deep neural networks, to better understand these recent relative successes and help design better algorithms in the future.

Asynchronous Methods for Deep Reinforcement Learning

A conceptually simple and lightweight framework for deep reinforcement learning that uses asynchronous gradient descent for optimization of deep neural network controllers and shows that asynchronous actor-critic succeeds on a wide variety of continuous motor control problems as well as on a new task of navigating random 3D mazes using a visual input.

Human-level control through deep reinforcement learning

This work bridges the divide between high-dimensional sensory inputs and actions, resulting in the first artificial agent that is capable of learning to excel at a diverse array of challenging tasks.

Deep Reinforcement Learning with Double Q-Learning

This paper proposes a specific adaptation to the DQN algorithm and shows that the resulting algorithm not only reduces the observed overestimations, as hypothesized, but that this also leads to much better performance on several games.

Reducing the Dimensionality of Data with Neural Networks

This work describes an effective way of initializing the weights that allows deep autoencoder networks to learn low-dimensional codes that work much better than principal components analysis as a tool to reduce the dimensionality of data.

Imagination-Augmented Agents for Deep Reinforcement Learning

Imagination-Augmented Agents (I2As), a novel architecture for deep reinforcement learning combining model-free and model-based aspects, shows improved data efficiency, performance, and robustness to model misspecification compared to several baselines.

Mastering the game of Go with deep neural networks and tree search

Using this search algorithm, the program AlphaGo achieved a 99.8% winning rate against other Go programs, and defeated the human European Go champion by 5 games to 0.5, the first time that a computer program has defeated a human professional player in the full-sized game of Go.

TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems

The TensorFlow interface and an implementation of that interface that is built at Google are described, which has been used for conducting research and for deploying machine learning systems into production across more than a dozen areas of computer science and other fields.

StarCraft II: A New Challenge for Reinforcement Learning

This paper introduces SC2LE (StarCraft II Learning Environment), a reinforcement learning environment based on the StarCraft II game that offers a new and challenging environment for exploring deep reinforcement learning algorithms and architectures and gives initial baseline results for neural networks trained from this data to predict game outcomes and player actions.