Deep reinforcement learning with double q-learning
The popular Q-learning algorithm is known to overestimate action values under certain
conditions. It was not previously known whether, in practice, such overestimations are …
conditions. It was not previously known whether, in practice, such overestimations are …
[PDF][PDF] PILCO: A model-based and data-efficient approach to policy search
M Deisenroth, CE Rasmussen - Proceedings of the 28th …, 2011 - aiweb.cs.washington.edu
In this paper, we introduce pilco, a practical, data-efficient model-based policy search
method. Pilco reduces model bias, one of the key problems of model-based reinforcement …
method. Pilco reduces model bias, one of the key problems of model-based reinforcement …
[图书][B] Reinforcement learning: An introduction
The significantly expanded and updated new edition of a widely used text on reinforcement
learning, one of the most active research areas in artificial intelligence. Reinforcement …
learning, one of the most active research areas in artificial intelligence. Reinforcement …
Learning values across many orders of magnitude
Most learning algorithms are not invariant to the scale of the signal that is being
approximated. We propose to adaptively normalize the targets used in the learning updates …
approximated. We propose to adaptively normalize the targets used in the learning updates …
Reinforcement learning in continuous state and action spaces
H Van Hasselt - Reinforcement Learning: State-of-the-Art, 2012 - Springer
Many traditional reinforcement-learning algorithms have been designed for problems with
small finite state and action spaces. Learning in such discrete problems can been difficult …
small finite state and action spaces. Learning in such discrete problems can been difficult …
Deep reinforcement learning for clinical decision support: a brief survey
Owe to the recent advancements in Artificial Intelligence especially deep learning, many
data-driven decision support systems have been implemented to facilitate medical doctors in …
data-driven decision support systems have been implemented to facilitate medical doctors in …
Towards 5G: A reinforcement learning-based scheduling solution for data traffic management
Dominated by delay-sensitive and massive data applications, radio resource management
in 5G access networks is expected to satisfy very stringent delay and packet loss …
in 5G access networks is expected to satisfy very stringent delay and packet loss …
[PDF][PDF] Weighted double Q-learning.
Z Zhang, Z Pan, MJ Kochenderfer - IJCAI, 2017 - ijcai.org
Q-learning is a popular reinforcement learning algorithm, but it can perform poorly in
stochastic environments due to overestimating action values. Overestimation is due to the …
stochastic environments due to overestimating action values. Overestimation is due to the …
Reducing estimation bias via triplet-average deep deterministic policy gradient
The overestimation caused by function approximation is a well-known property in Q-learning
algorithms, especially in single-critic models, which leads to poor performance in practical …
algorithms, especially in single-critic models, which leads to poor performance in practical …
Unifying task specification in reinforcement learning
M White - International Conference on Machine Learning, 2017 - proceedings.mlr.press
Reinforcement learning tasks are typically specified as Markov decision processes. This
formalism has been highly successful, though specifications often couple the dynamics of …
formalism has been highly successful, though specifications often couple the dynamics of …