Search Results for author: Tobias Joppen

Found 5 papers, 1 papers with code

Ordinal Monte Carlo Tree Search

no code implementations26 Jan 2021 Tobias Joppen, Johannes Fürnkranz

In this paper we take a look at MCTS, a popular algorithm to solve MDPs, highlight a reoccurring problem concerning its use of rewards, and show that an ordinal treatment of the rewards overcomes this problem.

Ordinal Bucketing for Game Trees using Dynamic Quantile Approximation

no code implementations31 May 2019 Tobias Joppen, Tilman Strübig, Johannes Fürnkranz

In this paper, we present a simple and cheap ordinal bucketing algorithm that approximately generates $q$-quantiles from an incremental data stream.

Deep Ordinal Reinforcement Learning

1 code implementation6 May 2019 Alexander Zap, Tobias Joppen, Johannes Fürnkranz

Reinforcement learning usually makes use of numerical rewards, which have nice properties but also come with drawbacks and difficulties.

OpenAI Gym Q-Learning

Ordinal Monte Carlo Tree Search

no code implementations14 Jan 2019 Tobias Joppen, Johannes Fürnkranz

In many problem settings, most notably in game playing, an agent receives a possibly delayed reward for its actions.

Preference-Based Monte Carlo Tree Search

no code implementations17 Jul 2018 Tobias Joppen, Christian Wirth, Johannes Fürnkranz

To deal with such cases, the experimenter has to supply an additional numeric feedback signal in the form of a heuristic, which intrinsically guides the agent.

Cannot find the paper you are looking for? You can Submit a new open access paper.