Lade Veranstaltungen

« Alle Veranstaltungen

  • Diese Veranstaltung hat bereits stattgefunden.

136. PDG: Simple Statistical Gradient-Following Algorithms

Februar 6 @ 7:00 pm

In the Paper Discussion Group (PDG) we discuss on a weekly base recent and fundamental papers in the area of machine learning. For several weeks, we follow one track to dive a bit deeper into a topic by reading matching or correlate papers. If you are interested, please read the paper and join us.

We start the new track AlphaStar. We follow the recent success of Deepminds AlphaStar system (https://deepmind.com/blog/alphastar-mastering-real-time-strategy-game-starcraft-ii/) which beats human professional players in the game StarCraft II. Our goal is to understand the techniques behind this success and start therefore an extended track.
We will start with the very basics and read papers which builds on each other. So we start with Williams ’92.

Track: AlphaStar
Topic: Simple Statistical Gradient-Following Algorithms for
Connectionist Reinforcement Learning
Paper: http://citeseerx.ist.psu.edu/viewdoc/download;jsessionid=0F64B3E06107F374445F46860741DA11?doi=10.1.1.129.8871&rep=rep1&type=pdf

The potential next papers:
Model-Free Reinforcement Learning with Continuous Action in Practice
Asynchronous Methods for Deep Reinforcement Learning
StarCraft II: A New Challenge for Reinforcement Learning
Attention Is All You Need
IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
DEEP REINFORCEMENT LEARNING WITH RELATIONAL
INDUCTIVE BIASES
Pointer Networks
A Unified Game-Theoretic Approach to Multiagent Reinforcement Learning
Human-level control through deep reinforcement learning
Counterfactual Multi-Agent Policy Gradients
Population Based Training of Neural Networks
Human-level performance in first-person multiplayer games with population-based deep reinforcement learning

Wir treffen uns im Informatik-Gebäude des KIT (50.34), Raum -120. Wenn alle Teilnehmer Mutterspachler sind, sind die Diskussionen sind auf deutsch.
Meetup: https://www.meetup.com/de-DE/karlsruhe-ai

Details

Datum:
Februar 6
Zeit:
7:00 pm
Website:
http://www.ml-ka.de

Veranstalter

ML-KA

Hinterlasse ein Kommentar