Unverified50% confidenceFactExact time
The researchers propose APSD (Asymmetric Policy Optimization via Self-Distillation), which balances behavior preservation and error correction by constructing a correctness-dependent asymmetric target distribution.
1
Sources
50%
Confidence
Long-term
Relevance
10/20/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedFor incorrect rollouts, APSD adopts an extrapolation strategy, extending the target distribution beyond the self-teacher to strengthen correction.72% similarUnverifiedOccupancy-measure-based algorithms rewrite the policy optimization problem as convex optimization over the occupancy measure polytope, thereby globally controlling error accumulation across all state-action pairs, which is the fundamental reason their regret bound has one fewer H factor.69% similarUnverifiedThe core insight of the paper is that quantization allocation should not stop at sensitivity ranking, but should shift toward objective-aware allocation, that is, reverse-calibrating each expert's error weight according to the final optimization objective.66% similarUnverifiedWriting only one position or conditionally independent positions per step can theoretically match the distribution exactly, while writing more dependent positions causes errors to accumulate.66% similarUnverifiedStrategies for addressing error accumulation include Monte Carlo tree search-style lookahead planning, hierarchical planning, and confidence-based adaptive execution.65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1074084API
curl https://kongchang.com/api/v1/knowledge/claims/1074084MCP
get_claim(id=1074084)