Learning deep neural network policies with continuous memory states

By Marvin Zhang, Zoe McCarthy, Chelsea Finn, Sergey Levine, Pieter Abbeel. 2015

95 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

A Survey of Deep Network Solutions for Learning Control in Robotics: From Reinforcement to Imitation (2016, neutral): “ocesses. The trialand-error process may lead to serious damage to real systems. Most of the reinforcement learning applications in robotics are trained in simulation environments (Tai and Liu, 2016a; Zhang et al., 2016a). However, model learned in simulation alone unfortunately cannot be directly tr”
Cognitive Mapping and Planning for Visual Navigation (2017, neutral): “Follow-up works (Mnih et al. 2016; Gu et al. 2016; Schulman et al. 2015) propose improvements to DRL algorithms, (Oh et al. 2016; Mnih et al. 2016; Wierstra et al. 2010; Heess et al. 2015; Zhang et al. 2016) study how to incorporate memory into such neural network based models.”
Opponent Modeling in Deep Reinforcement Learning (2016, background): “Rewards r are assigned by a real-valued reward function R ( s, a, s (cid:48) ) . such The agent’s behavior is deﬁned by a policy π that π ( a s ) is the probability of taking action a in state s .”
Memory Augmented Control Networks (2017, background): “[8] showed that when learning how to plan in such environments, it becomes necessary to use memory to retain information about states visited.”
A Deep Policy Inference Q-Network for Multi-Agent Systems (2017, background): “In recent years, a special field called deep reinforcement learning (DRL), which combines RL and deep neural networks (DNNs), has shown great successes in a wide variety of single-agent stationary settings, including Atari games [14, 26], robot navigation [37], and Go [31].”
Sim2Real Viewpoint Invariant Visual Servoing by Recurrent Control (2018, methodology): “The use of recurrent networks for control has previously been used in a number of works on reinforcement learning, including methods for visual navigation [22, 24], continuous control [13, 38], and physics simulation to real world transfer [25] without visual observations.”
Decentralized non-communicating multiagent collision avoidance with deep reinforcement learning (2016, background): “While applications of RL are typically limited to discrete, low-dimensional domains, recent advances in Deep RL [20]– [22] have demonstrated human-level performance in complex, high-dimensional spaces.”
Scene Memory Transformer for Embodied Agents in Long-Horizon Tasks (2019, background): “To enhance agent’s ability to plan and reason, neural network policies with external memories have been pro-Scene posed [32, 49].”
Knowledge Transfer for Deep Reinforcement Learning with Hierarchical Experience Replay (2017, background): “…sensory inputs in many challenging task domains, such as arcade game playing (Mnih et al. 2015; Van Hasselt, Guez, and Silver 2016), robotic manipulation (Levine et al. 2016; Finn, Levine, and Abbeel 2016), and natural language processing (Zhang et al. 2016; Li et al. 2016; Guo 2015).”
Diversity-Driven Exploration Strategy for Deep Reinforcement Learning (2018, background): “In recent years, deep reinforcement learning (DRL) has attracted attention in a variety of application domains, such as game playing [1, 2] and robot navigation [3].”
Deep-learning in Mobile Robotics - from Perception to Control Systems: A Survey on Why and Why not (2016, methodology): “Most of the reinforcement learning applications in robotics are trained in simulation environments (Tai and Liu, 2016a; Zhang et al., 2016a).”
Sim2Real View Invariant Visual Servoing by Recurrent Control (2017, background): “The use of recurrent networks for control has previously been explored in a number of works on reinforcement learning, including methods for navigation [22, 24], continuous control [13, 38], and simulation to real world transfer [25].”
A Review of Deep Learning Methods and Applications for Unmanned Aerial Vehicles (2017, methodology): “DNN-based GPS has been widely applied to robotic control, from manipulation to navigation tasks [35, 36].”
Imitation Learning (2017, background): “Recurrent neural networks are incorporated into guided policy search in Zhang et al. [2016] to facilitate dealing with partially observed problems.”