- What would Jiminy Cricket do?: A pluralist approach in generating and processing morally-aligned text
- Natural Language Processing and Reinforcement Learning to Generate Morally Aligned Text: Comparing a moral agent to an optimally playing agent
- Balancing multidimensional morality and progression: Evaluating the tradeoff for artificial agents playing text-based games
- Inverse Reinforcement Learning (IRL) in Presence of Risk and Uncertainty Related Cognitive Biases: To what extent can IRL learn rewards from expert demonstrations with loss and risk aversion?
- What are the implications of Curriculum Learning strategy on IRL methods?: Investigating Inverse Reinforcement Learning from Human Behavior
- Replacing the acquisition function in Bayesian optimization by a neural network: How effectively do meta-learned acquisition functions in Bayesian optimization perform when optimizing for control variates of unknown functions, as compared to BO with standard acquisition functions
- Effects of Partial Observability Solver Methods on Training and Final Policies in Autonomous Driver RL: How do different methods for dealing with partial observability in the environment influence training and the robustness of final policies under various testing conditions?
- Fictional Co-Play for Human-Agent Collaboration: Evaluating state-of-the-art reinforcement learning technique for adaptability to human collaborators
- Improving a Reinforcement Learning Negotiating Agent’s Performance by Extracting Information from the Opponent’s Sequence of Offers
- Reinforcement Learning for Switching of Semiautomated Vehicles Under Uncomfortable Driving Situations