Improved empirical methods in reinforcement-learning evaluation

10 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Doubly Robust Off-policy Value Evaluation for Reinforcement Learning (2015, background): “In some discounted problems the true horizon is inﬁnite, but for the purpose of policy value evaluation we can still use a ﬁnite H (usually set to be on the order of O (1 / (1 − γ )) ) so that v π,H approximates v π, ∞ with a bounded error that diminishes as H increases.”
A Unified Game-Theoretic Approach to Multiagent Reinforcement Learning (2017, background): “There has been relatively little work done in RL community on overfitting to the environment [102, 69], but we argue that this is particularly important in multiagent settings where one must react dynamically based on the observed behavior of others.”
Recurrent Reinforcement Learning: A Hybrid Approach (2015, methodology): “rs of RNN for DQN training, and do not involve in the RNN training. 4 EXPERIMENTS 4.1 DATASET In this paper, we use the 1998 KDD Cup direct mailing dataset1, which has been used in the RL literature (Marivate, 2015; Pednault et al., 2002) for various purposes. It was collected by a nonproﬁt organiza”
Arena: A General Evaluation Platform and Building Toolkit for Multi-Agent Intelligence (2019, background): “When solving more practical problems, many issues have been raised, such as ensuring diversity amongst agents [58, 98], avoiding overfitting to the policy of the opponents [46, 48, 59, 65, 78].”