What is catastrophic forgetting in foundation models? Foundation models excel in diverse domains but are largely static once deployed. Fine-tuning on new tasks often introduces catastrophic forgetting—the loss of previously learned capabilities. This limitation poses a barrier for building long-lived, continually improving AI agents. Why does online reinforcement learning forget less than supervised fine-tuning? A […] The post A New MIT Study Shows Reinforcement Learning Minimizes Catastrophic Forgetting Compared to Supervised Fine-Tuning appeared first on MarkTechPost.
A New MIT Study Shows Reinforcement Learning Minimizes Catastrophic Forgetting Compared to Supervised Fine-Tuning
What is catastrophic forgetting in foundation models? Foundation models excel in diverse domains but are largely static once deployed. Fine-tuning on new tasks often introduces catastrophic forgetting—the loss of previously learned capabilities. This limitation poses a barrier for building long-lived, continually improving AI agents. Why does online reinforcement learning forget less than supervised fine-tuning? A […] The post A New MIT Study Shows Reinforcement Learning Minimizes Catastrophic Forgetting Compared to Supervised Fine-Tuning appeared first on MarkTechPost.