Research

Bottom-up Multi-Agent Reinforcement Learning
A reward shaping method for multi-agent systems where each agent has an individual task.
Last updated on Mar 1, 2024
Bottom-up Multi-Agent Reinforcement Learning
Meta-Optimization of Bias-Variance Trade-Off
A meta-optimization method to balance bias-variance trade-offs in model learning for a meta-objective.
Last updated on Mar 1, 2024
Meta-Optimization of Bias-Variance Trade-Off
Reward-Punishment Actor-Critic Algorithm
An actor-critic algorithm for safety policy learning by considering risk.
Last updated on Mar 1, 2024
Reward-Punishment Actor-Critic Algorithm