2nd/10_Wiki/Topics/AI_and_ML/Policy-Gradient-Methods.md

id, title, category, status, canonical_id, duplicate_of, aliases, source_trust_level, confidence_score, verification_status, tags, last_reinforced, github_commit

id	title	category	status	canonical_id	duplicate_of	aliases	source_trust_level	confidence_score	verification_status	tags	last_reinforced	github_commit
wiki-2026-0508-policy-gradient-methods	Policy Gradient Methods	10_Wiki/Topics	duplicate	policy-optimization	Policy-Optimization		A	0.9	redirected	duplicate reinforcement-learning policy-gradient	2026-05-10	pending

Policy Gradient Methods

이 문서는 Policy-Optimization 의 중복본입니다. Canonical 문서로 redirect.

핵심 요약 (PG-specific aspects)

• 매 policy gradient = ∇J = E[∇log π · A] — 매 foundational identity.
• 매 REINFORCE → A2C → TRPO → PPO → GRPO → DPO 매 lineage 매 Policy-Optimization 에 정리.
• 매 vanilla PG 매 high variance — 매 baseline + GAE 의 mitigate.

🔗 Graph

• 부모: Policy-Optimization (canonical)

🕓 변경 이력

날짜	변경
2026-05-08	Phase 1
2026-05-10	중복 처리 — canonical 문서로 redirect