Search Results for author: Adi Makmal

Found 5 papers, 0 papers with code

Benchmarking projective simulation in navigation problems

no code implementations23 Apr 2018 Alexey A. Melnikov, Adi Makmal, Hans J. Briegel

Projective simulation (PS) is a model for intelligent agents with a deliberation capacity that is based on episodic memory.

Benchmarking Q-Learning +2

Meta-learning within Projective Simulation

no code implementations25 Feb 2016 Adi Makmal, Alexey A. Melnikov, Vedran Dunjko, Hans J. Briegel

The extended model is examined on three different kinds of reinforcement learning tasks, in which the agent has different optimal values of the meta-parameters, and is shown to perform well, reaching near-optimal to optimal success rates in all of them, without ever needing to manually adjust any meta-parameter.

Meta-Learning reinforcement-learning +1

Projective simulation with generalization

no code implementations9 Apr 2015 Alexey A. Melnikov, Adi Makmal, Vedran Dunjko, Hans J. Briegel

Specifically, we show that already in basic (but extreme) environments, learning without generalization may be impossible, and demonstrate how the presented generalization machinery enables the projective simulation agent to learn.

Projective simulation applied to the grid-world and the mountain-car problem

no code implementations21 May 2014 Alexey A. Melnikov, Adi Makmal, Hans J. Briegel

We compare the performance of the PS agent model with those of existing models and show that the PS agent exhibits competitive performance also in such scenarios.

Benchmarking reinforcement-learning +1

Projective simulation for classical learning agents: a comprehensive investigation

no code implementations7 May 2013 Julian Mautner, Adi Makmal, Daniel Manzano, Markus Tiersch, Hans J. Briegel

We study the model of projective simulation (PS), a novel approach to artificial intelligence based on stochastic processing of episodic memory which was recently introduced [H. J.


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