Marco Pleines

Publication Activity (10 Years)

Years Active: 2019-2023
Publications (10 Years): 10

Top Topics

Partially Observable

Reinforcement Learning

Top Venues

Publications

Marco Pleines, Matthias Pallasch, Frank Zimmer, Mike Preuss
Memory Gym: Partially Observable Challenges to Memory-Based Agents in Endless Episodes. CoRR (2023)
Marco Pleines, Matthias Pallasch, Frank Zimmer, Mike Preuss
Memory Gym: Partially Observable Challenges to Memory-Based Agents. ICLR (2023)
Marco Pleines, Konstantin Ramthun, Yannik Wegener, Hendrik Meyer, Matthias Pallasch, Sebastian Prior, Jannik Drögemüller, Leon Büttinghaus, Thilo Röthemeyer, Alexander Kaschwig, Oliver Chmurzynski, Frederik Rohkrähmer, Roman Kalkreuth, Frank Zimmer, Mike Preuss
On the Verge of Solving Rocket League using Deep Reinforcement Learning and Sim-to-sim Transfer. CoRR (2022)
Jonas Schumacher, Marco Pleines
Improving Bidding and Playing Strategies in the Trick-Taking game Wizard using Deep Q-Networks. CoRR (2022)
Marco Pleines, Konstantin Ramthun, Yannik Wegener, Hendrik Meyer, Matthias Pallasch, Sebastian Prior, Jannik Drögemüller, Leon Büttinghaus, Thilo Röthemeyer, Alexander Kaschwig, Oliver Chmurzynski, Frederik Rohkrähmer, Roman Kalkreuth, Frank Zimmer, Mike Preuss
On the Verge of Solving Rocket League using Deep Reinforcement Learning and Sim-to-sim Transfer. CoG (2022)
Marco Pleines, Matthias Pallasch, Frank Zimmer, Mike Preuss
Generalization, Mayhems and Limits in Recurrent Proximal Policy Optimization. CoRR (2022)
Jonas Schumacher, Marco Pleines
Improving Bidding and Playing Strategies in the Trick-Taking game Wizard using Deep Q-Networks. CoG (2022)
Marco Pleines, Jenia Jitsev, Mike Preuss, Frank Zimmer
Obstacle Tower Without Human Demonstrations: How Far a Deep Feed-Forward Network Goes with Reinforcement Learning. CoRR (2020)
Marco Pleines, Jenia Jitsev, Mike Preuss, Frank Zimmer
Obstacle Tower Without Human Demonstrations: How Far a Deep Feed-Forward Network Goes with Reinforcement Learning. CoG (2020)
Marco Pleines, Frank Zimmer, Vincent-Pierre Berges
Action Spaces in Deep Reinforcement Learning to Mimic Human Input Devices. CoG (2019)