AI bots told to act as trading agents in simulated markets engaged in pervasive collusion, raising new questions about how financial regulators have previously addressed this tech.

Taking a bot trained with VPT and fine-tuning it with reinforcement learning allowed it to carry out tasks involving more than 20,000 consecutive actions.

This study seeks to construct a basic reinforcement learning-based AI-macroeconomic simulator. We use a deep RL (DRL) approach (DDPG) in an RBC macroeconomic model. We set up two learning scenarios, ...

Microsoft's Azure Cognitive Services introduced new AI tools today, including Personalizer, which uses reinforcement learning to improve recommendations.

Rather than generating potential outcomes based on historical data, deep reinforcement learning teaches AI agents and machines with the time-tested "carrot and stick" method.

Reinforcement learning techniques could be the keys to integrating robots — who use machine learning to output more than words — into the real world.