Other formats:
BibTeX
LaTeX
RIS
@inproceedings{1674916, author = {Brázdil, Tomáš and Chatterjee, Krishnendu and Novotný, Petr and Vahala, Jiří}, address = {Palo Alto, California, USA}, booktitle = {The Thirty-Fourth AAAI Conference on Artificial Intelligence, AAAI 2020}, doi = {http://dx.doi.org/10.1609/aaai.v34i06.6531}, keywords = {reinforcement learning; Markov decision processes; Monte Carlo tree search; risk aversion}, howpublished = {elektronická verze "online"}, language = {eng}, location = {Palo Alto, California, USA}, isbn = {978-1-57735-823-7}, pages = {9794-9801}, publisher = {AAAI Press}, title = {Reinforcement Learning of Risk-Constrained Policies in Markov Decision Processes}, url = {https://aaai.org/ojs/index.php/AAAI/article/view/6531}, year = {2020} }
TY - JOUR ID - 1674916 AU - Brázdil, Tomáš - Chatterjee, Krishnendu - Novotný, Petr - Vahala, Jiří PY - 2020 TI - Reinforcement Learning of Risk-Constrained Policies in Markov Decision Processes PB - AAAI Press CY - Palo Alto, California, USA SN - 9781577358237 KW - reinforcement learning KW - Markov decision processes KW - Monte Carlo tree search KW - risk aversion UR - https://aaai.org/ojs/index.php/AAAI/article/view/6531 L2 - https://aaai.org/ojs/index.php/AAAI/article/view/6531 N2 - Markov decision processes (MDPs) are the defacto framework for sequential decision making in the presence of stochastic uncertainty. A classical optimization criterion for MDPs is to maximize the expected discounted-sum payoff, which ignores low probability catastrophic events with highly negative impact on the system. On the other hand, risk-averse policies require the probability of undesirable events to be below a given threshold, but they do not account for optimization of the expected payoff. We consider MDPs with discounted-sum payoff with failure states which represent catastrophic outcomes. The objective of risk-constrained planning is to maximize the expected discounted-sum payoff among risk-averse policies that ensure the probability to encounter a failure state is below a desired threshold. Our main contribution is an efficient risk-constrained planning algorithm that combines UCT-like search with a predictor learned through interaction with the MDP (in the style of AlphaZero) and with a risk-constrained action selection via linear programming. We demonstrate the effectiveness of our approach with experiments on classical MDPs from the literature, including benchmarks with an order of 10^6 states. ER -
BRÁZDIL, Tomáš, Krishnendu CHATTERJEE, Petr NOVOTNÝ and Jiří VAHALA. Reinforcement Learning of Risk-Constrained Policies in Markov Decision Processes. Online. In \textit{The Thirty-Fourth AAAI Conference on Artificial Intelligence, AAAI 2020}. Palo Alto, California, USA: AAAI Press, 2020, p.~9794-9801. ISBN~978-1-57735-823-7. Available from: https://dx.doi.org/10.1609/aaai.v34i06.6531.
|