Train An Imaginative Agent
A seemingly reasonable push in Sokoban can make the puzzle unsolvable. To avoid such mistakes, an agent has to anticipate the consequences of its actions before execution, especially when feedback from the real environment is sparse or actions are irreversible. We introduce Agentic Imagination (Agima), a training framework that trains an agent to imagine before acting, i.e. to be imaginative.…
We haven't written up this one. arXiv cs.AI has the full story — the link below goes straight to it.