Task Scheduling & Forgetting in Multi-Task Reinforcement Learning
This addresses the issue of forgetting in multi-task RL agents, which is incremental as it builds on existing human forgetting research but shows limited transferability of prevention measures.
The study tackled the problem of task forgetting in multi-task reinforcement learning agents, finding that they exhibit forgetting curves similar to humans, but methods effective for humans, like Leitner or SuperMemo, do not transfer well to RL, likely due to asymmetrical learning and retention patterns between tasks.
Reinforcement learning (RL) agents can forget tasks they have previously been trained on. There is a rich body of work on such forgetting effects in humans. Therefore we look for commonalities in the forgetting behavior of humans and RL agents across tasks and test the viability of forgetting prevention measures from learning theory in RL. We find that in many cases, RL agents exhibit forgetting curves similar to those of humans. Methods like Leitner or SuperMemo have been shown to be effective at counteracting human forgetting, but we demonstrate they do not transfer as well to RL. We identify a likely cause: asymmetrical learning and retention patterns between tasks that cannot be captured by retention-based or performance-based curriculum strategies.