An opponent-aware Q-learning scheme, built on level-k reasoning and Bayesian averaging over adversary types, improves robustness and exploitability in security games and repeated matrix games.
Configurable Markov Decision Processes
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
In many real-world problems, there is the possibility to configure, to a limited extent, some environmental parameters to improve the performance of a learning agent. In this paper, we propose a novel framework, Configurable Markov Decision Processes (Conf-MDPs), to model this new type of interaction with the environment. Furthermore, we provide a new learning algorithm, Safe Policy-Model Iteration (SPMI), to jointly and adaptively optimize the policy and the environment configuration. After having introduced our approach and derived some theoretical results, we present the experimental evaluation in two explicative problems to show the benefits of the environment configurability on the performance of the learned policy.
fields
cs.LG 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Opponent Aware Reinforcement Learning
An opponent-aware Q-learning scheme, built on level-k reasoning and Bayesian averaging over adversary types, improves robustness and exploitability in security games and repeated matrix games.