Topic Tag: DQN

home Forums Topic Tag: DQN

 Combating Reinforcement Learning’s Sisyphean Curse with Intrinsic Fear

  

To use deep reinforcement learning in the wild, we might hope for an agent that can avoid catastrophic mistakes. Unfortunately, even in simple environments, the popular deep Q-network (DQN) algorithm is doomed by a Sisyphean curse. Owing to the use of function approximation, these agents may eventu…


 Combating Reinforcement Learning’s Sisyphean Curse with Intrinsic Fear

  

To use deep reinforcement learning in the wild, we might hope for an agent that can avoid catastrophic mistakes. Unfortunately, even in simple environments, the popular deep Q-network (DQN) algorithm is doomed by a Sisyphean curse. Owing to the use of function approximation, these agents may eventu…


 Combating Reinforcement Learning’s Sisyphean Curse with Intrinsic Fear

  

To use deep reinforcement learning in the wild, we might hope for an agent that can avoid catastrophic mistakes. Unfortunately, even in simple environments, the popular deep Q-network (DQN) algorithm is doomed by a Sisyphean curse. Owing to the use of function approximation, these agents may eventu…


 Rainbow: Combining Improvements in Deep Reinforcement Learning

  

The deep reinforcement learning community has made several independent improvements to the DQN algorithm. However, it is unclear which of these extensions are complementary and can be fruitfully combined. This paper examines six extensions to the DQN algorithm and empirically studies their combinat…


 Multi-Level Discovery of Deep Options

  

Augmenting an agent’s control with useful higher-level behaviors called options can greatly reduce the sample complexity of reinforcement learning, but manually designing options is infeasible in high-dimensional and abstract state spaces. While recent work has proposed several techniques for…


 Deep Abstract Q-Networks

  

We examine the problem of learning and planning on high-dimensional domains with long horizons and sparse rewards. Recent approaches have shown great successes in many Atari 2600 domains. However, domains with long horizons and sparse rewards, such as Montezuma’s Revenge and Venture, remain c…


 Learning to Drive using Inverse Reinforcement Learning and Deep Q-Networks

  

We propose an inverse reinforcement learning (IRL) approach using Deep Q-Networks to extract the rewards in problems with large state spaces. We evaluate the performance of this approach in a simulation-based autonomous driving scenario. Our results resemble the intuitive relation between the rewar…


 Revisiting the Arcade Learning Environment: Evaluation Protocols and Open Problems for General Agents

 

The Arcade Learning Environment (ALE) is an evaluation platform that poses the challenge of building AI agents with general competency across dozens of Atari 2600 games. It supports a variety of different problem settings and it has been receiving increasing attention from the scientific community,…


 The Uncertainty Bellman Equation and Exploration

  

We consider the exploration/exploitation problem in reinforcement learning. For exploitation, it is well known that the Bellman equation connects the value at any time-step to the expected value at subsequent time-steps. In this paper we consider a similar uncertainty Bellman equation (UBE), which …


 Automated Cloud Provisioning on AWS using Deep Reinforcement Learning

 

As the use of cloud computing continues to rise, controlling cost becomes increasingly important. Yet there is evidence that 30% – 45% of cloud spend is wasted. Existing tools for cloud provisioning typically rely on highly trained human experts to specify what to monitor, thresholds for trig…


 Pre-training Neural Networks with Human Demonstrations for Deep Reinforcement Learning

   

Deep reinforcement learning (deep RL) has achieved superior performance in complex sequential tasks by using a deep neural network as its function approximator and by learning directly from raw images. A drawback of using raw images is that deep RL must learn the state feature representation from t…


 Deep Reinforcement Learning with Surrogate Agent-Environment Interface

  

In this paper we propose surrogate agent-environment interface (SAEI) in reinforcement learning. We also state that learning based on probability surrogate agent-environment interface gives optimal policy of task agent-environment interface. We introduce surrogate probability action and develope th…


 Autonomous Quadrotor Landing using Deep Reinforcement Learning

  

Landing an unmanned aerial vehicle on a ground marker is an open problem despite the effort of the research community. Previous attempts mostly focused on the analysis of hand-crafted geometric features and the use of external sensors in order to allow the vehicle to approach the land-pad. In this …


 Formulation of Deep Reinforcement Learning Architecture Toward Autonomous Driving for On-Ramp Merge

     

Multiple automakers have in development or in production automated driving systems (ADS) that offer freeway-pilot functions. This type of ADS is typically limited to restricted-access freeways only, that is, the transition from manual to automated modes takes place only after the ramp merging proce…


 Deep Reinforcement Learning: An Overview

      

We give an overview of recent exciting achievements of deep reinforcement learning (RL). We discuss six core elements, six important mechanisms, and twelve applications. We start with background of machine learning, deep learning and reinforcement learning. Next we discuss core RL elements, includi…


 OpenAI Baselines: DQN

 

We’re open-sourcing OpenAI Baselines, our internal effort to reproduce reinforcement learning algorithms with performance on par with published results. We’ll release the algorithms over upcoming months; today’s release includes DQN and three of its variants. Reinforcement learnin…