Open AccessProceedings Article
Prioritized Experience Replay
TLDR
Prioritized experience replay as mentioned in this paper is a framework for prioritizing experience, so as to replay important transitions more frequently, and therefore learn more efficiently, achieving human-level performance across many Atari games.Abstract:
Experience replay lets online reinforcement learning agents remember and reuse experiences from the past. In prior work, experience transitions were uniformly sampled from a replay memory. However, this approach simply replays transitions at the same frequency that they were originally experienced, regardless of their significance. In this paper we develop a framework for prioritizing experience, so as to replay important transitions more frequently, and therefore learn more efficiently. We use prioritized experience replay in Deep Q-Networks (DQN), a reinforcement learning algorithm that achieved human-level performance across many Atari games. DQN with prioritized experience replay achieves a new state-of-the-art, outperforming DQN with uniform replay on 41 out of 49 games.read more
Citations
More filters
Journal ArticleDOI
Deep Reinforcement Learning Techniques in Diversified Domains: A Survey
TL;DR: It is found that even after obtaining good results in Atari, Go, Robotics, multi-agent scenarios, there are challenges such as generalization, satisfying multiple objectives, divergence, learning robust policy.
Posted Content
Memory Augmented Policy Optimization for Program Synthesis with Generalization
TL;DR: Memory Augmented Policy Optimization (MAPO), a novel policy optimization formulation that incorporates a memory buffer of promising trajectories to reduce the variance of policy gradient estimates for deterministic environments with discrete actions, is presented.
Journal ArticleDOI
QoE-Oriented Rate Adaptation for DASH With Enhanced Deep Q-Learning
Jie Liu,Xiaoming Tao,Jianhua Lu +2 more
TL;DR: The proposed RDQ agent has been thoroughly evaluated using trace-based simulation on the real-time LTE network data and shows that RDQ can suppress the number and the duration of the stalling events to the minimum while maintaining high video bitrate, thus achieving better QoE performance than other methods.
Journal ArticleDOI
Energy-Efficient Mobile Crowdsensing by Unmanned Vehicles: A Sequential Deep Reinforcement Learning Approach
Chengzhe Piao,Chi Harold Liu +1 more
TL;DR: This article proposes a novel sequential deep model called “PPO+LSTM,” which contains a sequential model LSTM and is trained with proximal policy optimization (PPO), for assigning tasks and planning route, and shows that the solution outperforms all others in terms of energy efficiency, data collection ratio, and geographic fairness.
Proceedings ArticleDOI
Motion Control for Biped Robot via DDPG-based Deep Reinforcement Learning
TL;DR: In this paper, the Deep Deterministic Policy Gradient (DDPG) is proposed to control the biped robot walk steadily on the slope and can walk stably, indicating that DDPG can effectively control the fall over of the biping robot.
References
More filters
Proceedings Article
Adam: A Method for Stochastic Optimization
Diederik P. Kingma,Jimmy Ba +1 more
TL;DR: This work introduces Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments, and provides a regret bound on the convergence rate that is comparable to the best known results under the online convex optimization framework.
Journal ArticleDOI
Gradient-based learning applied to document recognition
Yann LeCun,Léon Bottou,Léon Bottou,Yoshua Bengio,Yoshua Bengio,Yoshua Bengio,Patrick Haffner +6 more
TL;DR: In this article, a graph transformer network (GTN) is proposed for handwritten character recognition, which can be used to synthesize a complex decision surface that can classify high-dimensional patterns, such as handwritten characters.
Journal ArticleDOI
Human-level control through deep reinforcement learning
Volodymyr Mnih,Koray Kavukcuoglu,David Silver,Andrei Rusu,Joel Veness,Marc G. Bellemare,Alex Graves,Martin Riedmiller,Andreas K. Fidjeland,Georg Ostrovski,Stig Petersen,Charles Beattie,Amir Sadik,Ioannis Antonoglou,Helen King,Dharshan Kumaran,Daan Wierstra,Shane Legg,Demis Hassabis +18 more
TL;DR: 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.
Posted Content
Playing Atari with Deep Reinforcement Learning
Volodymyr Mnih,Koray Kavukcuoglu,David Silver,Alex Graves,Ioannis Antonoglou,Daan Wierstra,Martin Riedmiller +6 more
TL;DR: This work presents the first deep learning model to successfully learn control policies directly from high-dimensional sensory input using reinforcement learning, which outperforms all previous approaches on six of the games and surpasses a human expert on three of them.
Proceedings ArticleDOI
A discriminatively trained, multiscale, deformable part model
TL;DR: A discriminatively trained, multiscale, deformable part model for object detection, which achieves a two-fold improvement in average precision over the best performance in the 2006 PASCAL person detection challenge and outperforms the best results in the 2007 challenge in ten out of twenty categories.
Related Papers (5)
Human-level control through deep reinforcement learning
Mastering the game of Go with deep neural networks and tree search
David Silver,Aja Huang,Chris J. Maddison,Arthur Guez,Laurent Sifre,George van den Driessche,Julian Schrittwieser,Ioannis Antonoglou,Veda Panneershelvam,Marc Lanctot,Sander Dieleman,Dominik Grewe,John Nham,Nal Kalchbrenner,Ilya Sutskever,Timothy P. Lillicrap,Madeleine Leach,Koray Kavukcuoglu,Thore Graepel,Demis Hassabis +19 more