Switching reinforcement learning for continuous action space

2012 ◽  
Vol 95 (3) ◽  
pp. 37-44
Author(s):  
Masato Nagayoshi ◽  
Hajime Murao ◽  
Hisashi Tamaki
Keyword(s):  
Reinforcement Learning ◽  
Action Space ◽  
Continuous Action

scholarly journals A game strategy model in the digital curling system based on NFSP

2021 ◽  
Author(s):  
Yuntao Han ◽  
Qibin Zhou ◽  
Fuqing Duan
Keyword(s):  
Reinforcement Learning ◽  
Nash Equilibrium ◽  
Action Space ◽  
Learning Networks ◽  
Game Tree ◽  
Continuous Action ◽  
Extensive Game ◽  
Strategy Model ◽  
Zero Sum ◽  
Tree Searching

AbstractThe digital curling game is a two-player zero-sum extensive game in a continuous action space. There are some challenging problems that are still not solved well, such as the uncertainty of strategy, the large game tree searching, and the use of large amounts of supervised data, etc. In this work, we combine NFSP and KR-UCT for digital curling games, where NFSP uses two adversary learning networks and can automatically produce supervised data, and KR-UCT can be used for large game tree searching in continuous action space. We propose two reward mechanisms to make reinforcement learning converge quickly. Experimental results validate the proposed method, and show the strategy model can reach the Nash equilibrium.

Switching Reinforcement Learning for Continuous Action Space

2011 ◽  
Vol 131 (5) ◽  
pp. 976-982
Author(s):  
Masato Nagayoshi ◽  
Hajime Murao ◽  
Hisashi Tamaki
Keyword(s):  
Reinforcement Learning ◽  
Action Space ◽  
Continuous Action

A reinforcement learning with switching controllers for a continuous action space

2010 ◽  
Vol 15 (1) ◽  
pp. 97-100 ◽  
Author(s):  
Masato Nagayoshi ◽  
Hajime Murao ◽  
Hisashi Tamaki
Keyword(s):  
Reinforcement Learning ◽  
Action Space ◽  
Continuous Action

scholarly journals Goal-Oriented Obstacle Avoidance with Deep Reinforcement Learning in Continuous Action Space

Electronics ◽  
2020 ◽  
Vol 9 (3) ◽  
pp. 411
Author(s):  
Reinis Cimurs ◽  
Jin Han Lee ◽  
Il Hong Suh
Keyword(s):  
Reinforcement Learning ◽  
Obstacle Avoidance ◽  
Action Space ◽  
Polar Coordinates ◽  
Depth Image ◽  
Depth Information ◽  
Continuous Action ◽  
Learning Network ◽  
Complex Shapes ◽  
Policy Gradient

In this paper, we propose a goal-oriented obstacle avoidance navigation system based on deep reinforcement learning that uses depth information in scenes, as well as goal position in polar coordinates as state inputs. The control signals for robot motion are output in a continuous action space. We devise a deep deterministic policy gradient network with the inclusion of depth-wise separable convolution layers to process the large amounts of sequential depth image information. The goal-oriented obstacle avoidance navigation is performed without prior knowledge of the environment or a map. We show that through the proposed deep reinforcement learning network, a goal-oriented collision avoidance model can be trained end-to-end without manual tuning or supervision by a human operator. We train our model in a simulation, and the resulting network is directly transferred to other environments. Experiments show the capability of the trained network to navigate safely around obstacles and arrive at the designated goal positions in the simulation, as well as in the real world. The proposed method exhibits higher reliability than the compared approaches when navigating around obstacles with complex shapes. The experiments show that the approach is capable of avoiding not only static, but also dynamic obstacles.

Sign in / Sign up

Export Citation Format

Share Document