Learning to play visual doom using model-free episodic control

Min, Byeong-Jun; Kim, Kyung Joong

doi:10.1109/cig.2017.8080439

Cited by 6 publications

(2 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…An episode starts when the first frame of the match is rendered, and ends when the end-of-game condition is detected. A single trial consists of 3,000 episodes in which RawReward are collected and evaluated [30], [31]. The game Assault, seen in Fig.…”

Section: A Training Environmentsmentioning

confidence: 99%

Difference Based Metrics for Deep Reinforcement Learning Algorithms

et al. 2019

View full text Add to dashboard Cite

Although state-of-the-art deep reinforcement learning often achieves superhuman levels on some tasks, the authors still struggle to analyze, compare or report the obtained results due to the unstable nature of the algorithms and the diversity of metrics used in the literature. Furthermore, these metrics fail to show some characteristics of the learning process, leading to misinterpretations by the analyst. The objective of this paper is to propose, implement and analyze a difference based evaluation metric that highlight different aspects of the learning process, allowing for more detailed results and analysis that can be used by automated software or analysts, experienced or not. A possible applicability for the proposed metric is to create automated evaluation systems, that can detect anomalies during the training process automatically.INDEX TERMS Machine learning, artificial intelligence (AI), differential equations, metrics.

show abstract

Section: A Training Environmentsmentioning

confidence: 99%

Difference Based Metrics for Deep Reinforcement Learning Algorithms

et al. 2019

View full text Add to dashboard Cite

show abstract

“…In the last few years, reinforcement learning (RL) combined with deep learning has been able to achieve remarkable success in various areas such as robotics [1], [2], [3], continuous control [4], [5] and video games [6], [7], [8]. For example, [7] build an RL agent which could achieve a super human like performance and beat the world champion in the game of Go.…”

Section: Introductionmentioning

confidence: 99%

Deep Reinforcement Learning based Vehicle Navigation amongst pedestrians using a Grid-based state representation

Deshpande

Spalanzani

2019

2019 IEEE Intelligent Transportation Systems Conference (ITSC)

View full text Add to dashboard Cite

Autonomous navigation in structured urban environments amongst pedestrians is a challenging and less explored problem. In this work, we propose to use a deep reinforcement learning based method to solve this problem of navigation. A Deep Q-Network based agent is trained in a simulator for a typical intersection crossing setup amongst pedestrians. We propose a grid based representation as a state space input to the learning agent. With this grid based representation and our reward function the agent learns a policy capable of driving safely around pedestrians and also follow the traffic rules.

show abstract