2016
DOI: 10.48550/arxiv.1609.07845
|View full text |Cite
Preprint
|
Sign up to set email alerts
|

Decentralized Non-communicating Multiagent Collision Avoidance with Deep Reinforcement Learning

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
15
0

Year Published

2017
2017
2023
2023

Publication Types

Select...
3
2

Relationship

0
5

Authors

Journals

citations
Cited by 6 publications
(15 citation statements)
references
References 0 publications
0
15
0
Order By: Relevance
“…Reinforcement Learning (RL) methods have been intensively studied over the last few years and applied to various fields since it started to achieve superior performance in video games [35]. In the field of robot navigation, recent works have used RL to learn sensorimotor policies in static and dynamic environments from the raw observations [21], [36] and socially cooperative policies with the agent-level state information [19], [20], [22]. To handle a variant number of neighbors, the method reported in [19] adapts from the two-agent to the multi-agent case through a maximin operation that picks up the best action against the worstcase for the crowd.…”
Section: Background a Related Workmentioning
confidence: 99%
See 3 more Smart Citations
“…Reinforcement Learning (RL) methods have been intensively studied over the last few years and applied to various fields since it started to achieve superior performance in video games [35]. In the field of robot navigation, recent works have used RL to learn sensorimotor policies in static and dynamic environments from the raw observations [21], [36] and socially cooperative policies with the agent-level state information [19], [20], [22]. To handle a variant number of neighbors, the method reported in [19] adapts from the two-agent to the multi-agent case through a maximin operation that picks up the best action against the worstcase for the crowd.…”
Section: Background a Related Workmentioning
confidence: 99%
“…In the field of robot navigation, recent works have used RL to learn sensorimotor policies in static and dynamic environments from the raw observations [21], [36] and socially cooperative policies with the agent-level state information [19], [20], [22]. To handle a variant number of neighbors, the method reported in [19] adapts from the two-agent to the multi-agent case through a maximin operation that picks up the best action against the worstcase for the crowd. A later extension uses an LSTM model to process the state of each neighbor sequentially in reverse order of the distance to the robot [22].…”
Section: Background a Related Workmentioning
confidence: 99%
See 2 more Smart Citations
“…Imitation learning [79][80] is also used to collect high-quality data for network initialization, therefore network can converge faster (e.g. deep V learning [81][82]). Existing methods in data collection work well, therefore it is hard to make further optimization.…”
Section: B Comparisons Of Convergence Speed and Stabilitymentioning
confidence: 99%