Picture for Mike Preuss

Mike Preuss

Illuminating the Diversity-Fitness Trade-Off in Black-Box Optimization

Add code
Aug 29, 2024
Viaarxiv icon

World Models Increase Autonomy in Reinforcement Learning

Add code
Aug 20, 2024
Viaarxiv icon

Memory Gym: Partially Observable Challenges to Memory-Based Agents in Endless Episodes

Add code
Sep 29, 2023
Viaarxiv icon

Believable Minecraft Settlements by Means of Decentralised Iterative Planning

Add code
Sep 19, 2023
Viaarxiv icon

Models Matter: The Impact of Single-Step Retrosynthesis on Synthesis Planning

Add code
Aug 10, 2023
Viaarxiv icon

Two-Memory Reinforcement Learning

Add code
Apr 23, 2023
Viaarxiv icon

Mind the Retrosynthesis Gap: Bridging the divide between Single-step and Multi-step Retrosynthesis Prediction

Add code
Dec 12, 2022
Viaarxiv icon

First Go, then Post-Explore: the Benefits of Post-Exploration in Intrinsic Motivation

Add code
Dec 06, 2022
Viaarxiv icon

Continuous Episodic Control

Add code
Nov 28, 2022
Viaarxiv icon

On the Verge of Solving Rocket League using Deep Reinforcement Learning and Sim-to-sim Transfer

Add code
May 24, 2022
Figure 1 for On the Verge of Solving Rocket League using Deep Reinforcement Learning and Sim-to-sim Transfer
Figure 2 for On the Verge of Solving Rocket League using Deep Reinforcement Learning and Sim-to-sim Transfer
Figure 3 for On the Verge of Solving Rocket League using Deep Reinforcement Learning and Sim-to-sim Transfer
Figure 4 for On the Verge of Solving Rocket League using Deep Reinforcement Learning and Sim-to-sim Transfer
Viaarxiv icon