67 citations · 192 across the 14 of their papers we have counts for
4 papers · 1 filter
Learning High-Risk High-Precision Motion Control
Nam Hee Kim, Markus Kirjonen, Perttu Hämäläinen
Deep reinforcement learning (DRL) algorithms for movement control are typically evaluated and benchmarked on sequential decision tasks where imprecise actions may be corrected with…
Deep Residual Mixture Models
Perttu Hämäläinen, Martin Trapp, Tuure Saloheimo +1
We propose Deep Residual Mixture Models (DRMMs), a novel deep generative model architecture. Compared to other deep models, DRMMs allow more flexible conditional sampling: The mode…
PPO-CMA: Proximal Policy Optimization with Covariance Matrix Adaptation
Perttu Hämäläinen, Amin Babadi, Xiaoxiao Ma +1
Proximal Policy Optimization (PPO) is a highly popular model-free reinforcement learning (RL) approach. However, we observe that in a continuous action space, PPO can prematurely s…
An Iterative Closest Points Approach to Neural Generative Models
Joose Rajamäki, Perttu Hämäläinen
We present a simple way to learn a transformation that maps samples of one distribution to the samples of another distribution. Our algorithm comprises an iteration of 1) drawing s…