Top suggestions for Constrained Policy OptimizationExplore more searches like Constrained Policy OptimizationPeople interested in Constrained Policy Optimization also searched for |
Related Products
+algorithms+have+shown+tremendous+success+in+simulation+environments%252C+but+their+application+to+real-world+problems+faces+significant+challenges%252C+with+safety+being+a+major+concern.+In+particular%252C+enforcing+state-wise+constraints+is+essential+for+many+challenging+tasks+such+as+autonomous+driving+and+robot+manipulation.+However%252C+existing+safe+RL+algorithms+under+the+framework+of+Constrained+Markov+Decision+Process+(CMDP)+do+not+consider+state-wise+constraints.+To+address+this+gap%252C+we+propose+State-wise+Constrained+Policy+Optimization+(SCPO)%252C+the+first+general-purpose+policy+search+algorithm+for+state-wise+constrained+reinforcement+learning.+SCPO+provides+guarantees+for+state-wise+constraint+satisfaction+in+expectation.+In+particular%252C+we+introduce+the+framework+of+Maximum+Markov+Decision+Process%252C+and+prove+that+the+worst-case+safety+violation+is+bounded+under+SCPO.+We+demonstrate+the+effectiveness+of+our+approach+on+training+neural+network+policies+for+extensive+robot+locomotion+tasks%252C+where+the+agent+must+satisfy+a+variety+of+state-wise+safety+constraints.+Our+results+show+that+SCPO+significantly+outperforms+existing+methods+and+can+handle+state-wise+constraints+in+high-dimensional+robotics+tasks.&cdnurl=https%3a%2f%2fth.bing.com%2fth%2fid%2fR.d2fea69f980728ba45ad29b127d92b15%3frik%3d4Xs6Gr3793opNg%26pid%3dImgRaw%26r%3d0&exph=630&expw=1200&q=Constrained+Policy+Optimization&simid=608034239186894144&FORM=IRPRST&ck=B1BE1A319CF4BE953BFF740841C14611&selectedIndex=22&itb=0)
Some results have been hidden because they may be inaccessible to you.Show inaccessible results
Feedback