161 citations · 1k across the 77 of their papers we have counts for
15 papers · 1 filter
Combining Bayesian Inference and Reinforcement Learning for Agent Decision Making: A Review
Chengmin Zhou, Ville Kyrki, Pasi Fränti +1
Bayesian inference has many advantages in decision making of agents (e.g. robotics/simulative agent) over a regular data-driven black-box neural network: Data-efficiency, generaliz…
COSBO: Conservative Offline Simulation-Based Policy Optimization
Eshagh Kargar, Ville Kyrki
Offline reinforcement learning allows training reinforcement learning models on data from live deployments. However, it is limited to choosing the best combination of behaviors pre…
From Alexnet to Transformers: Measuring the Non-linearity of Deep Neural Networks with Affine Optimal Transport
Quentin Bouniot, Ievgen Redko, Anton Mallasto +6
In the last decade, we have witnessed the introduction of several novel deep neural network (DNN) architectures exhibiting ever-increasing performance across diverse tasks. Explain…
Learning representations that are closed-form Monge mapping optimal with application to domain adaptation
Oliver Struckmeier, Ievgen Redko, Anton Mallasto +3
Optimal transport (OT) is a powerful geometric tool used to compare and align probability measures following the least effort principle. Despite its widespread use in machine learn…
Co-Imitation: Learning Design and Behaviour by Imitation
Chang Rajani, Karol Arndt, David Blanco-Mulero +2
The co-adaptation of robots has been a long-standing research endeavour with the goal of adapting both body and behaviour of a system for a given task, inspired by the natural evol…
Training and Evaluation of Deep Policies using Reinforcement Learning and Generative Models
Ali Ghadirzadeh, Petra Poklukar, Karol Arndt +4
We present a data-efficient framework for solving sequential decision-making problems which exploits the combination of reinforcement learning (RL) and latent variable generative m…
Vision Transformer for Learning Driving Policies in Complex Multi-Agent Environments
Eshagh Kargar, Ville Kyrki
Driving in a complex urban environment is a difficult task that requires a complex decision policy. In order to make informed decisions, one needs to gain an understanding of the l…
MACRPO: Multi-Agent Cooperative Recurrent Policy Optimization
Eshagh Kargar, Ville Kyrki
This work considers the problem of learning cooperative policies in multi-agent settings with partially observable and non-stationary environments without a communication channel.…
Evolving-Graph Gaussian Processes
David Blanco-Mulero, Markus Heinonen, Ville Kyrki
Graph Gaussian Processes (GGPs) provide a data-efficient solution on graph structured domains. Existing approaches have focused on static structures, whereas many real graph data r…
Domain Curiosity: Learning Efficient Data Collection Strategies for Domain Adaptation
Karol Arndt, Oliver Struckmeier, Ville Kyrki
Domain adaptation is a common problem in robotics, with applications such as transferring policies from simulation to real world and lifelong learning. Performing such adaptation,…
Increasing the Efficiency of Policy Learning for Autonomous Vehicles by Multi-Task Representation Learning
Eshagh Kargar, Ville Kyrki
Driving in a dynamic, multi-agent, and complex urban environment is a difficult task requiring a complex decision-making policy. The learning of such a policy requires a state repr…
Autoencoding Slow Representations for Semi-supervised Data Efficient Regression
Oliver Struckmeier, Kshitij Tiwari, Ville Kyrki
The slowness principle is a concept inspired by the visual cortex of the brain. It postulates that the underlying generative factors of a quickly varying sensory signal change on a…
Few-shot model-based adaptation in noisy conditions
Karol Arndt, Ali Ghadirzadeh, Murtaza Hazara +1
Few-shot adaptation is a challenging problem in the context of simulation-to-real transfer in robotics, requiring safe and informative data collection. In physical systems, additio…
Notes on the Behavior of MC Dropout
Francesco Verdoja, Ville Kyrki
Among the various options to estimate uncertainty in deep neural networks, Monte-Carlo dropout is widely popular for its simplicity and effectiveness. However the quality of the un…
From Video Game to Real Robot: The Transfer between Action Spaces
Janne Karttunen, Anssi Kanervisto, Ville Kyrki +1
Deep reinforcement learning has proven to be successful for learning tasks in simulated environments, but applying same techniques for robots in real-world domain is more challengi…