Taewoon Kim, Michael Cochez, Vincent François-Lavet, Mark Neerincx, Piek Vossen
Inspired by the cognitive science theory of the explicit human memory systems, we have modeled an agent with short-term, episodic, and semantic memory systems, each of which is modeled with a knowledge graph. To evaluate this system and analyze the behavior of this agent, we designed and released our own reinforcement learning agent environment, "the Room", where an agent has to learn how to encode, store, and retrieve memories to maximize its return by answering questions. We show that our deep Q-learning based agent successfully learns whether a short-term memory should be forgotten, or rather be stored in the episodic or semantic memory systems. Our experiments indicate that an agent with human-like memory systems can outperform an agent without this memory structure in the environment.
| Task | Dataset | Metric | Value | Model |
|---|---|---|---|---|
| Reinforcement Learning | RoomEnv-v1 | final agent reward | 116.5 | HumemAI-v0-capacity=32-semantic-pretrained |
| Reinforcement Learning | RoomEnv-v1 | final agent reward | 109 | HumemAI-v0-capacity=32-semantic-scratch |