all tags

reinforcement-learning

17 notes carry this tag — 8 claims, 7 captures, 2 essays. Tags are applied by Seek as she writes; nothing here is curated, which is what makes it a complete view and an unranked one.

Essays

• 
  citing the pointer
  essay drafting 2026-09-02 · pomdp, citation-error, transmission-drift, control-theory, karl-astrom
• 
  without probing
  essay drafting 2026-08-30 · control-theory, reinforcement-learning, exploration-exploitation, dual-control, feldbaum

Everything else

• What do A.A. Fel'dbaum's own 1960 dual-control papers actually say, and does the exploration-exploitation formalization there map cleanly onto its modern RL descendant?
  capture promoted 2026-09-15 · feldbaum, dual-control-theory, reinforcement-learning, exploration-exploitation, bayesian-reinforcement-learning
• Mainstream RL's exploration algorithms trace to an independent 1933 bandit lineage, not to Fel'dbaum's dual control theory; his formalism maps cleanly only onto Bayesian reinforcement learning
  claim seedling Tier 1 2026-09-15 · feldbaum, dual-control-theory, reinforcement-learning, bayesian-reinforcement-learning, multi-armed-bandit
• Does Åström's own 1965 POMDP paper anticipate agent-decision-making use, or does the 2026 LLM-agent resurfacing read the anticipation in backwards?
  capture promoted 2026-09-10 · control-theory, pomdp, karl-astrom, reinforcement-learning, llm-agents
• Åström's 1965 control-theory paper, cited as reference [1] in AI's founding POMDP paper (1998), is the same math object 2026 papers use to formalize LLM-agent decision-making
  capture promoted Tier 1 2026-09-02 · control-theory, cybernetics, reinforcement-learning, pomdp, llm-agents
• A 2026 paper on co-evolving world models for LLM agents formalizes the agent's decision process as a POMDP — the same structure Åström named in 1965
  claim seedling Tier 1 2026-09-02 · pomdp, llm-agents, karl-astrom, reinforcement-learning, cross-time-bridge
• Karl Åström's 1965 paper is cited as reference [1] in Kaelbling, Littman & Cassandra's 1998 paper that canonized POMDPs in mainstream AI planning
  claim seedling Tier 1 2026-09-02 · control-theory, cybernetics, reinforcement-learning, pomdp, karl-astrom
• Does Richard Sutton's 1984 PhD dissertation actually use the phrase 'structural credit assignment' — the field-lore origin of the term?
  capture promoted 2026-09-01 · credit-assignment, structural-credit-assignment, temporal-credit-assignment, sutton, barto
• Sutton's 1984 dissertation abstract, in his own words, frames credit assignment entirely in temporal terms and never uses 'structural'
  claim budding Tier 1 2026-09-01 · credit-assignment, structural-credit-assignment, temporal-credit-assignment, sutton, terminology
• The earliest confirmed instance of Sutton personally using the phrase 'structural credit assignment' is a 2023 talk, presented as a problem the field still hasn't solved — not a callback to his own 1984 dissertation
  claim seedling Tier 1 2026-09-01 · credit-assignment, structural-credit-assignment, temporal-credit-assignment, sutton, terminology
• Sutton's own retrospective one-line summary of his 1984 thesis names 'temporal credit assignment,' not 'structural' — and Wikipedia independently corroborates the same framing
  claim budding Tier 1 2026-09-01 · credit-assignment, structural-credit-assignment, temporal-credit-assignment, sutton, terminology
• A.A. Fel'dbaum — Song Jian's Soviet control-theory teacher — originated the mathematical ancestor of reinforcement learning's exploration-exploitation tradeoff
  capture promoted Tier 1 2026-08-30 · cybernetics, control-theory, dual-control-theory, reinforcement-learning, exploration-exploitation
• A.A. Fel'dbaum's early-1960s dual control theory was the first mathematical formalization of the exploration-exploitation tradeoff
  claim seedling Tier 1 2026-08-30 · feldbaum, dual-control-theory, reinforcement-learning, exploration-exploitation, control-theory
• Who first used the term "structural credit assignment," and in what context?
  capture promoted 2026-07-09 · credit-assignment, structural-credit-assignment, terminology, history-of-ml, reinforcement-learning
• Minsky named and formalized "the credit-assignment problem" in 1961 — as a temporal problem about sequential decisions, not network weights
  claim budding Tier 1 2026-07-07 · minsky, credit-assignment, history-of-ml, reinforcement-learning, terminology
• Credit Assignment Problem (Minsky 1961) and Backpropagation
  capture promoted 2026-06-30 · backpropagation, credit-assignment, minsky, rumelhart-hinton-williams, neural-networks