Topic Tag: Reinforcement Learning

home Forums Topic Tag: Reinforcement Learning

 Faster Deep Q-learning using Neural Episodic Control

  

The Research on deep reinforcement learning to estimate Q-value by deep learning has been active in recent years. In deep reinforcement learning, it is important to efficiently learn the experiences that a agent has collected by exploring the environment. In this research, we propose NEC2DQN that i…


 Crossmodal Attentive Skill Learner

  

This paper presents the Crossmodal Attentive Skill Learner (CASL), integrated with the recently-introduced Asynchronous Advantage Option-Critic (A2OC) architecture [Harb et al., 2017] to enable hierarchical reinforcement learning across multiple sensory inputs. We provide concrete examples where th…


 Deep Reinforcement Learning of Cell Movement in the Early Stage of C. elegans Embryogenesis

 

Cell movement in the early phase of C. elegans development is regulated by a highly complex process in which a set of rules and connections are formulated at distinct scales. Previous efforts have demonstrated that agent-based, multi-scale modeling systems can integrate physical and biological rule…


 Deep Reinforcement Fuzzing

  

Fuzzing is the process of finding security vulnerabilities in input-processing code by repeatedly testing the code with modified inputs. In this paper, we formalize fuzzing as a reinforcement learning problem using the concept of Markov decision processes. This in turn allows us to apply state-of-t…


 Evaluation of Machine Learning Fameworks on Finis Terrae II

 

Machine Learning (ML) and Deep Learning (DL) are two technologies used to extract representations of the data for a specific purpose. ML algorithms take a set of data as input to generate one or several predictions. To define the final version of one model, usually there is an initial step devoted …


 Cooperative Multi-Agent Reinforcement Learning for Low-Level Wireless Communication

 

Traditional radio systems are strictly co-designed on the lower levels of the OSI stack for compatibility and efficiency. Although this has enabled the success of radio communications, it has also introduced lengthy standardization processes and imposed static allocation of the radio spectrum. Vari…


 Model-Based Action Exploration

 

Deep reinforcement learning has great stride in solving challenging motion control tasks. Recently there has been a significant amount of work on methods to exploit the data gathered during training, but less work is done on good methods for generating data to learn from. For continuous actions dom…


 Neural Program Synthesis with Priority Queue Training

   

We consider the task of program synthesis in the presence of a reward function over the output of programs, where the goal is to find programs with maximal rewards. We employ an iterative optimization scheme, where we train an RNN on a dataset of K best programs from a priority queue of the generat…


 DeepTraffic: Driving Fast through Dense Traffic with Deep Reinforcement Learning

  

We present a micro-traffic simulation (named “DeepTraffic”) where the perception, control, and planning systems for one of the cars are all handled by a single neural network as part of a model-free, off-policy reinforcement learning process. The primary goal of DeepTraffic is to make t…


 A dynamic connectome supports the emergence of stable computational function of neural circuits through reward-based learning

Synaptic connections between neurons in the brain are dynamic because of continuously ongoing spine dynamics, axonal sprouting, and other processes. In fact, it was recently shown that the spontaneous synapse-autonomous component of spine dynamics is at least as large as the component that depends …


 What do we need to build explainable AI systems for the medical domain?

    

Artificial intelligence (AI) generally and machine learning (ML) specifically demonstrate impressive practical success in many different application domains, e.g. in autonomous driving, speech recognition, or recommender systems. Deep learning approaches, trained on extremely large data sets or usi…


 PixelSNAIL: An Improved Autoregressive Generative Model

    

Autoregressive generative models consistently achieve the best results in density estimation tasks involving high dimensional data, such as images or audio. They pose density estimation as a sequence modeling task, where a recurrent neural network (RNN) models the conditional distribution over the …


 Ray RLLib: A Composable and Scalable Reinforcement Learning Library

Reinforcement learning (RL) algorithms involve the deep nesting of distinct components, where each component typically exhibits opportunities for distributed computation. Current RL libraries offer parallelism at the level of the entire program, coupling all the components together and making exist…


 Whatever Does Not Kill Deep Reinforcement Learning, Makes It Stronger

 

Recent developments have established the vulnerability of deep Reinforcement Learning (RL) to policy manipulation attacks via adversarial perturbations. In this paper, we investigate the robustness and resilience of deep RL to training-time and test-time attacks. Through experimental results, we de…


 Federated Control with Hierarchical Multi-Agent Deep Reinforcement Learning

We present a framework combining hierarchical and multi-agent deep reinforcement learning approaches to solve coordination problems among a multitude of agents using a semi-decentralized model. The framework extends the multi-agent learning setup by introducing a meta-controller that guides the com…


 A Deep Policy Inference Q-Network for Multi-Agent Systems

   

We present DPIQN, a deep policy inference Q-network that targets multi-agent systems composed of controllable agents, collaborators, and opponents that interact with each other. We focus on one challenging issue in such systems—modeling agents with varying strategies—and propose to empl…


 Multiagent-based Participatory Urban Simulation through Inverse Reinforcement Learning

The multiagent-based participatory simulation features prominently in urban planning as the acquired model is considered as the hybrid system of the domain and the local knowledge. However, the key problem of generating realistic agents for particular social phenomena invariably remains. The existi…


 Multi-shot Pedestrian Re-identification via Sequential Decision Making

   

Multi-shot pedestrian re-identification problem is at the core of surveillance video analysis. It matches two tracks of pedestrians from different cameras. In contrary to existing works that aggregate single frames features by time series model such as recurrent neural network, in this paper, we pr…


 ES Is More Than Just a Traditional Finite-Difference Approximator

 

An evolution strategy (ES) variant recently attracted significant attention due to its surprisingly good performance at optimizing neural networks in challenging deep reinforcement learning domains. It searches directly in the parameter space of neural networks by generating perturbations to the cu…


 Deep Neuroevolution: Genetic Algorithms Are a Competitive Alternative for Training Deep Neural Networks for Reinforcement Learning

     

Deep artificial neural networks (DNNs) are typically trained via gradient-based learning algorithms, namely backpropagation. Evolution strategies (ES) can rival backprop-based algorithms such as Q-learning and policy gradients on challenging deep reinforcement learning (RL) problems. However, ES ca…


 On the Relationship Between the OpenAI Evolution Strategy and Stochastic Gradient Descent

  

Because stochastic gradient descent (SGD) has shown promise optimizing neural networks with millions of parameters and few if any alternatives are known to exist, it has moved to the heart of leading approaches to reinforcement learning (RL). For that reason, the recent result from OpenAI showing t…


 Safe Mutations for Deep and Recurrent Neural Networks through Output Gradients

    

While neuroevolution (evolving neural networks) has a successful track record across a variety of domains from reinforcement learning to artificial life, it is rarely applied to large, deep neural networks. A central reason is that while random mutation generally works in low dimensions, a random p…


 Can Deep Reinforcement Learning Solve Erdos-Selfridge-Spencer Games?

 

Deep reinforcement learning has achieved many recent successes, but our understanding of its strengths and limitations is hampered by the lack of rich environments in which we can fully characterize optimal behavior, and correspondingly diagnose individual actions against such a characterization. H…


 Learning a Hierarchy

We’ve developed a hierarchical reinforcement learning algorithm that learns high-level actions useful for solving a range of tasks, allowing fast solving of tasks requiring thousands of timesteps. Our algorithm, when applied to a set of navigation problems, discovers a set of high-level actio…


 Online Monotone Games

  

Algorithmic game theory (AGT) focuses on the design and analysis of algorithms for interacting agents, with interactions rigorously formalized within the framework of games. Results from AGT find applications in domains such as online bidding auctions for web advertisements and network routing prot…