Driven by Compression Progress: A Simple Principle Explains Essential Aspects of Subjective Beauty, Novelty, Surprise, Interestingness, Attention, Curiosity, Creativity, Art, Science, Music, Jokes
What this work does
Intrinsic reward compares old and improved compressors on the same accumulated data; the controller seeks expected future compression progress. The appendix separates compression length, runtime cost and delayed compressor-improvement feedback.
Connection to discovery
A candidate discovery objective is improvement in an agent-relative explanatory code, not novelty or prediction error alone.
Evidence
This is a conceptual and algorithmic account with connections to earlier implementations, rather than a controlled modern scientific-agent benchmark.
Scope and limitations
Compressor choice and computational restrictions determine what is discoverable. The strongest optimal action-selection reference is incomputable; asynchronous improvement also creates a credit-assignment problem.
THE RESEARCH CONVERSATION
Discussion & reactions
Share a question, an insight, or a replication experience. Sign in with GitHub to join the conversation.