Interpretable experiential learning based on state history and global feedback

The paper introduces an interpretable experiential learning model that uses state history and global feedback to learn a behavioral model represented as a transition graph. Transitions in this graph are annotated with utility values and evidence counts, enabling the model to function in resource-constrained settings. The authors evaluate the approach on the OpenAI Gym Atari Breakout benchmark, showing performance comparable to certain neural network-based methods.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

• reinforcement-learning
• benchmarks