Search Results for author: Per-Arne Andersen

Found 17 papers, 6 papers with code

Contracting Tsetlin Machine with Absorbing Automata

no code implementations17 Oct 2023 Bimal Bhattarai, Ole-Christoffer Granmo, Lei Jiao, Per-Arne Andersen, Svein Anders Tunheim, Rishad Shafik, Alex Yakovlev

In brief, the TA of each clause literal has both an absorbing Exclude- and an absorbing Include state, making the learning scheme absorbing instead of ergodic.

Generalized Convergence Analysis of Tsetlin Machines: A Probabilistic Approach to Concept Learning

no code implementations3 Oct 2023 Mohamed-Bachir Belaid, Jivitesh Sharma, Lei Jiao, Ole-Christoffer Granmo, Per-Arne Andersen, Anis Yazidi

Tsetlin Machines (TMs) have garnered increasing interest for their ability to learn concepts via propositional formulas and their proven efficiency across various application domains.

Interpretable Machine Learning

Learning Minimalistic Tsetlin Machine Clauses with Markov Boundary-Guided Pruning

1 code implementation12 Sep 2023 Ole-Christoffer Granmo, Per-Arne Andersen, Lei Jiao, Xuan Zhang, Christian Blakely, Tor Tveit

A set of variables is the Markov blanket of a random variable if it contains all the information needed for predicting the variable.

Bayesian Inference

DeNISE: Deep Networks for Improved Segmentation Edges

no code implementations5 Sep 2023 Sander Riisøen Jyhne, Per-Arne Andersen, Morten Goodwin

This paper presents Deep Networks for Improved Segmentation Edges (DeNISE), a novel data enhancement technique using edge detection and segmentation models to improve the boundary quality of segmentation masks.

Edge Detection Segmentation

Loss and Reward Weighing for increased learning in Distributed Reinforcement Learning

no code implementations25 Apr 2023 Martin Holen, Per-Arne Andersen, Kristian Muri Knausgård, Morten Goodwin

This paper introduces two learning schemes for distributed agents in Reinforcement Learning (RL) environments, namely Reward-Weighted (R-Weighted) and Loss-Weighted (L-Weighted) gradient merger.

reinforcement-learning Reinforcement Learning (RL)

A Contrastive Learning Scheme with Transformer Innate Patches

1 code implementation26 Mar 2023 Sander Riisøen Jyhne, Per-Arne Andersen, Morten Goodwin

Contrastive Transformer enables existing contrastive learning techniques, often used for image classification, to benefit dense downstream prediction tasks such as semantic segmentation.

Contrastive Learning Image Segmentation +2

CaiRL: A High-Performance Reinforcement Learning Environment Toolkit

1 code implementation3 Oct 2022 Per-Arne Andersen, Morten Goodwin, Ole-Christoffer Granmo

CaiRL also presents the first reinforcement learning toolkit with a built-in JVM and Flash support for running legacy flash games for reinforcement learning research.

OpenAI Gym reinforcement-learning +2

Interpretable Option Discovery using Deep Q-Learning and Variational Autoencoders

no code implementations3 Oct 2022 Per-Arne Andersen, Ole-Christoffer Granmo, Morten Goodwin

We show that the DVQN algorithm is a promising approach for identifying initiation and termination conditions for option-based reinforcement learning.

Q-Learning reinforcement-learning +1

CostNet: An End-to-End Framework for Goal-Directed Reinforcement Learning

no code implementations3 Oct 2022 Per-Arne Andersen, Morten Goodwin, Ole-Christoffer Granmo

There are two approaches, model-based and model-free reinforcement learning, that show concrete results in several disciplines.

reinforcement-learning Reinforcement Learning (RL)

Towards Model-based Reinforcement Learning for Industry-near Environments

1 code implementation27 Jul 2019 Per-Arne Andersen, Morten Goodwin, Ole-Christoffer Granmo

If these environment dynamics are adequately learned, a model-based approach is perhaps the most sample efficient method for learning agents to act in an environment optimally.

Model-based Reinforcement Learning Q-Learning +2

Deep Q-Learning with Q-Matrix Transfer Learning for Novel Fire Evacuation Environment

no code implementations23 May 2019 Jivitesh Sharma, Per-Arne Andersen, Ole-Chrisoffer Granmo, Morten Goodwin

We also propose a new reinforcement learning approach that entails pretraining the network weights of a DQN based agents to incorporate information on the shortest path to the exit.

OpenAI Gym Q-Learning +3

The Dreaming Variational Autoencoder for Reinforcement Learning Environments

1 code implementation2 Oct 2018 Per-Arne Andersen, Morten Goodwin, Ole-Christoffer Granmo

It is likely that the solution to these problems lies in short- and long-term planning, exploration and memory management for reinforcement learning algorithms.

Management reinforcement-learning +1

Deep RTS: A Game Environment for Deep Reinforcement Learning in Real-Time Strategy Games

1 code implementation15 Aug 2018 Per-Arne Andersen, Morten Goodwin, Ole-Christoffer Granmo

Reinforcement learning (RL) is an area of research that has blossomed tremendously in recent years and has shown remarkable potential for artificial intelligence based opponents in computer games.

Reinforcement Learning (RL) Starcraft +1

FlashRL: A Reinforcement Learning Platform for Flash Games

no code implementations26 Jan 2018 Per-Arne Andersen, Morten Goodwin, Ole-Christoffer Granmo

This paper introduces the Flash Reinforcement Learning platform (FlashRL) which attempts to fill this gap by providing an environment for thousands of Flash games on a novel platform for Flash automation.

reinforcement-learning Reinforcement Learning (RL)

Towards a Deep Reinforcement Learning Approach for Tower Line Wars

no code implementations17 Dec 2017 Per-Arne Andersen, Morten Goodwin, Ole-Christoffer Granmo

We propose a game environment in between Atari 2600 and Starcraft II, particularly targeting Deep Reinforcement Learning algorithm research.

Q-Learning reinforcement-learning +3

Adaptive Task Assignment in Online Learning Environments

no code implementations23 Jun 2016 Per-Arne Andersen, Christian Kråkevik, Morten Goodwin, Anis Yazidi

As main contribution of this paper, we propose a a novel Skill-Based Task Selector (SBTS) algorithm which is able to approximate a student's skill level based on his performance and consequently suggest adequate assignments.

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