Getting AI to Cooperate: Sharing a Critic in a Video Game

Scripted AI for Overcooked: Designing and Evaluating a Scripted AI Controller for Simplified Overcooked

Cooperative AI for Overcooked: Multi-Agent RL with Population-Based Training

The Effects of Heuristic Optimisations on Planning Algorithms Within Cooperative AI: Cooperative Planning in Overcooked

Improvements in Imitation Learning for Overcooked

Multi-objective Deep Reinforcement Learning for predictive maintenance of road networks

Modelling Agents with Variational Autoencoders in Multi-Agent Sequential Decision Making

Pacing regulation for runners

Coupled and Model-based cooperative planning in Overcooked AI

Multi-Agent Reinforcement Learning using Centralized Critics in Collaborative Environments

Fictional Co-Play for Human-Agent Collaboration: Evaluating state-of-the-art reinforcement learning technique for adaptability to human collaborators

Smart Team Play: Utility of Population-Based Training for Cooperative AI in Overcooked

Evaluating Design Choices in Tripartite Graph-Based Recommender Systems to Improve Long Tail Recommendations

Minimizing the Long-tail Problem in Collaborative Filtering Based Recommender Systems Using Clustering

Adapting to Dynamic User Preferences in Recommendation Systems via Deep Reinforcement Learning

Alleviating the cold-start problem by using demographic data and domain-aware similarity measure

REAL Reinforcement Learning: Planning with adversarial models

Aligning AI with Human Norms: Multi-Objective Deep Reinforcement Learning with Active Preference Elicitation

Know what it does not know: Improving Offline Deep Reinforcement Learning with Uncertainty Estimation

An Exploration of a Hierarchical Approach for MacDec-POMDPs