Search Results for author:
Found 10 papers, 6 papers with code
Personalized Reinforcement Learning with a Budget of Policies
In an r-MDP, we cater to a diverse user population, each with unique preferences, through interaction with a small set of representative policies.
Mediated Multi-Agent Reinforcement Learning
The majority of Multi-Agent Reinforcement Learning (MARL) literature equates the cooperation of self-interested agents in mixed environments to the problem of social welfare maximization, allowing agents to arbitrarily share rewards and private information.
Neuromorphic Artificial Intelligence Systems
Modern AI systems, based on von Neumann architecture and classical neural networks, have a number of fundamental limitations in comparison with the brain.
Self-Imitation Learning from Demonstrations
Modern LfD algorithms require meticulous tuning of hyperparameters that control the influence of demonstrations and, as we show in the paper, struggle with learning from suboptimal demonstrations.
Improving State-of-the-Art in One-Class Classification by Leveraging Unlabeled Data
The former only learns from labeled positive data, whereas the latter also utilizes unlabeled data to improve the overall performance.
Optimal-er Auctions through Attention
The second is a loss function that requires explicit specification of an acceptable IC violation denoted as regret budget.
Neural Network Optimization for Reinforcement Learning Tasks Using Sparse Computations
This article proposes a sparse computation-based method for optimizing neural networks for reinforcement learning (RL) tasks.
Flatland Competition 2020: MAPF and MARL for Efficient Train Coordination on a Grid World
However, the coordination of hundreds of agents in a real-life setting like a railway network remains challenging and the Flatland environment used for the competition models these real-world properties in a simplified manner.
Balancing Rational and Other-Regarding Preferences in Cooperative-Competitive Environments
Recent reinforcement learning studies extensively explore the interplay between cooperative and competitive behaviour in mixed environments.
DEDPUL: Difference-of-Estimated-Densities-based Positive-Unlabeled Learning
The objectives are to classify the unlabeled sample and train an unbiased PN classifier, which generally requires to identify the mixing proportions of positives and negatives first.
