REVIEW 3 cited by
Goal Misgeneralization in Deep Reinforcement Learning
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
We study goal misgeneralization, a type of out-of-distribution generalization failure in reinforcement learning (RL). Goal misgeneralization failures occur when an RL agent retains its capabilities out-of-distribution yet pursues the wrong goal. For instance, an agent might continue to competently avoid obstacles, but navigate to the wrong place. In contrast, previous works have typically focused on capability generalization failures, where an agent fails to do anything sensible at test time. We formalize this distinction between capability and goal generalization, provide the first empirical demonstrations of goal misgeneralization, and present a partial characterization of its causes.
Forward citations
Cited by 3 Pith papers
-
When Does Reward Teach State? A Hidden-Automaton Instrument and the Group-Language Boundary
High reward in sparse RL does not imply latent-state recovery; a hidden-DFA instrument separates perception from planning gaps and flags group-language structure as a pre-training warning.
-
Draining the Energy Commons: Self-Defeating Over-Appropriation as a Coordination Failure in Agentic LLM Collectives
LLM prosumers deplete a shared renewable reserve exactly when demand exceeds peak replacement, acting like impatient open-access users even when sustaining the reserve is feasible.
-
Machine Theory of Mind and the Structure of Human Values
Human values are claimed to have a rational instrumental structure that lets AI infer unseen values from known ones, framing this as the 'value generalization problem' in AI safety.
Discussion (0). Continue with ORCID to comment.