Scipediacontent: Scipediacontent moved page Draft Content 442257307 to Klima et al 2019a

2021-02-01T22:53:06Z

Scipediacontent moved page Draft Content 442257307 to Klima et al 2019a

Scipediacontent: Created page with " == Abstract == We present a new Q-function operator for temporal difference (TD) learning methods that explicitly encodes robustness against significant rare events (SRE) in..."

2021-02-01T22:53:02Z

Created page with " == Abstract == We present a new Q-function operator for temporal difference (TD) learning methods that explicitly encodes robustness against significant rare events (SRE) in..."

New page

== Abstract ==

We present a new Q-function operator for temporal difference (TD) learning methods that explicitly encodes robustness against significant rare events (SRE) in critical domains. The operator, which we call the $\kappa$-operator, allows to learn a robust policy in a model-based fashion without actually observing the SRE. We introduce single- and multi-agent robust TD methods using the operator $\kappa$. We prove convergence of the operator to the optimal robust Q-function with respect to the model using the theory of Generalized Markov Decision Processes. In addition we prove convergence to the optimal Q-function of the original MDP given that the probability of SREs vanishes. Empirical evaluations demonstrate the superior performance of $\kappa$-based TD methods both in the early learning phase as well as in the final converged stage. In addition we show robustness of the proposed method to small model errors, as well as its applicability in a multi-agent context.

Comment: AAMAS 2019

== Original document ==

The different versions of the original document can be found in:

* [http://arxiv.org/abs/1901.08021 http://arxiv.org/abs/1901.08021]

* [https://ir.cwi.nl/pub/28689 https://ir.cwi.nl/pub/28689]

← Older revision	Revision as of 22:53, 1 February 2021
(No difference)

Klima et al 2019a - Revision history

Scipediacontent: Scipediacontent moved page Draft Content 442257307 to Klima et al 2019a

Scipediacontent: Created page with " == Abstract == We present a new Q-function operator for temporal difference (TD) learning methods that explicitly encodes robustness against significant rare events (SRE) in..."