scholarly journals Relational Reinforcement Learning with Continuous Actions by Combining Behavioural Cloning and Locally Weighted Regression

2010 ◽  
Vol 02 (02) ◽  
pp. 69-79 ◽  
Author(s):  
Julio H. Zaragoza ◽  
Eduardo F. Morales
Keyword(s):  
Reinforcement Learning ◽  
Weighted Regression ◽  
Locally Weighted Regression ◽  
Continuous Actions

PLAN VIEW PATTERN CONTROL FOR STEEL PLATES USING LOCALLY-WEIGHTED REGRESSION

2007 ◽  
Vol 40 (11) ◽  
pp. 125-130
Author(s):  
Hiroyasu Shigemori ◽  
Kouji Nanbu ◽  
Ryou Nagao ◽  
Tadashi Araki ◽  
Narihito Mizushima
Keyword(s):  
Steel Plates ◽  
Weighted Regression ◽  
Locally Weighted Regression ◽  
Plan View ◽  
Pattern Control ◽  
Plan View Pattern ◽  
Plan View Pattern Control

Application of locally weighted regression-based approach in correcting erroneous individual vehicle speed data

2015 ◽  
Vol 50 (2) ◽  
pp. 180-196 ◽  
Author(s):  
Heesub Rim ◽  
Seri Park ◽  
Cheol Oh ◽  
Junhyung Park ◽  
Gunwoo Lee
Keyword(s):  
Weighted Regression ◽  
Vehicle Speed ◽  
Locally Weighted Regression

scholarly journals Robust Multi-Agent Reinforcement Learning via Minimax Deep Deterministic Policy Gradient

2019 ◽  
Vol 33 ◽  
pp. 4213-4220 ◽  
Author(s):  
Shihui Li ◽  
Yi Wu ◽  
Xinyue Cui ◽  
Honghua Dong ◽  
Fei Fang ◽  
...  
Keyword(s):  
Reinforcement Learning ◽  
Gradient Algorithm ◽  
Training Environment ◽  
Local Optima ◽  
Continuous Action ◽  
Agent Learning ◽  
Policy Gradient ◽  
Multi Agent ◽  
Continuous Actions ◽  
Computational Intractability

Despite the recent advances of deep reinforcement learning (DRL), agents trained by DRL tend to be brittle and sensitive to the training environment, especially in the multi-agent scenarios. In the multi-agent setting, a DRL agent’s policy can easily get stuck in a poor local optima w.r.t. its training partners – the learned policy may be only locally optimal to other agents’ current policies. In this paper, we focus on the problem of training robust DRL agents with continuous actions in the multi-agent learning setting so that the trained agents can still generalize when its opponents’ policies alter. To tackle this problem, we proposed a new algorithm, MiniMax Multi-agent Deep Deterministic Policy Gradient (M3DDPG) with the following contributions: (1) we introduce a minimax extension of the popular multi-agent deep deterministic policy gradient algorithm (MADDPG), for robust policy learning; (2) since the continuous action space leads to computational intractability in our minimax learning objective, we propose Multi-Agent Adversarial Learning (MAAL) to efficiently solve our proposed formulation. We empirically evaluate our M3DDPG algorithm in four mixed cooperative and competitive multi-agent environments and the agents trained by our method significantly outperforms existing baselines.

Sign in / Sign up

Export Citation Format

Share Document