Dan Klein, Nicholas Tomlin, Andre He
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
We present a new dataset containing 10K human-annotated games of Go and show how these natural language annotations can be used as a tool for model interpretability. Given a board state and its associated comment, our approach uses linear probing to predict mentions of domain-specific terms (e.g., ko, atari) from the intermediate state representations of gameplaying agents like AlphaGo Zero. We find these game concepts are nontrivially encoded in two distinct policy networks, one trained via imitation learning and another trained via reinforcement learning. Furthermore, mentions of domain-specific terms are most easily predicted from the later layers of both models, suggesting that these policy networks encode high-level abstractions similar to those used in the natural language annotations.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2204.07531")
get_code_for_paper("2204.07531")
have("2204.07531")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2204.07531.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2204.07531)
Connect an agent — have() is free.