Skip to content
Last Dictionary
Plane
Agents & HarnessesPhilosophy & MindReinforcement Learning

episodic memory

nounAlso: episodic store

In plain wordsMemory of particular past events — what happened, when and in what order. AI agents keep records of earlier conversations or attempts so they can recall them and learn from them.

  1. 1

    Agents

    A store of records of an agent'sAI agent, n.: An AI system that does not just answer but acts: given a goal, it decides on steps, uses tools such as a browser or code editor, checks the results and keeps going until the job is done. specific past experiences — conversations, task attempts, trajectoriestrajectory, n.: The record of what happened as an AI agent acted: the sequence of situations it was in, the actions it took and the rewards it received., observations and outcomes — usually timestamped and retrieved by relevance or recency into the current contextcontext window, n.: How much an AI model can read and keep in view at once: the instructions, the conversation so far and any attached documents. Text that does not fit has to be cut, summarized or left out.. Examples include the memory stream of Generative Agents, which ranks memories by recency, importance and relevance and periodically distills them into higher-level reflections, and the self-critiques that ReflexionReflexion, prop. n.: A technique in which an AI agent that fails at a task writes itself a short note on what went wrong, then reads that note before trying again — learning from mistakes without retraining. agents store after failed attempts. Episodic memory lets an agent learn from experience without changing model weights; it is contrasted with semantic memory (general facts extracted from episodes) and procedural memory (skills).

    Before retrying the deployment, the agent searched its episodic memory for the last failure and its fix.

  2. 2

    Cognitive science and RL

    In psychology, memory for personally experienced events located in time and place, as opposed to semantic memory for facts. In reinforcement learningreinforcement learning, n.: A way of teaching a computer program by trial and error: it tries actions, earns points for good results and penalties for bad ones, and gradually learns which choices pay off over time., episodic control methods store individual past experiences and reuse their observed returns directly, which can learn faster than gradual value-function updates.

Origin

Endel Tulving distinguished episodic from semantic memory in a 1972 chapter, 'Episodic and Semantic Memory'. Reinforcement learning took the idea up in model-free episodic control (Charles Blundell et al., 2016). LLM-agent designs adopted it from 2023, notably in Generative Agents and the CoALA framework.

Related

See also
  • long-term memorylong-term memory, n.: Memory that lasts. For an AI agent, it means information saved outside the conversation — facts, past events, learned procedures — that can be looked up and used again days or months later.
  • agent memoryagent memory, n.: The ways an AI assistant or agent keeps information — your preferences, past conversations, lessons from earlier tasks — and brings it back later, beyond what fits in a single conversation.
  • working memoryworking memory, n.: The small amount of information held in mind right now while doing a task. For an AI model, that is roughly whatever currently sits in its context window.
  • ReflexionReflexion, prop. n.: A technique in which an AI agent that fails at a task writes itself a short note on what went wrong, then reads that note before trying again — learning from mistakes without retraining.
  • experience replayexperience replay, n.: Storing an AI agent's past experiences in a memory bank and repeatedly learning from random samples of them, rather than only from what just happened.
  • MemGPTMemGPT, prop. n.: A 2023 research system that gave a chatbot a computer-style memory hierarchy, letting it move information in and out of its limited working space so it could handle long documents and remember users.
Contrast with
  • parametric knowledgeparametric knowledge, n.: What an AI model 'knows' from training, stored in the numbers of its network rather than looked up in documents — like facts you have memorized rather than ones you check in a book.

Sources

  1. Tulving, E. (1972). Episodic and semantic memory. In E. Tulving & W. Donaldson (eds.), Organization of Memory. Academic Press.
  2. Park, J. S. et al. (2023). Generative Agents: Interactive Simulacra of Human Behavior. arXiv:2304.03442. arxiv.org/abs/2304.03442

Mentioned in

agent memoryagent memory, n.: The ways an AI assistant or agent keeps information — your preferences, past conversations, lessons from earlier tasks — and brings it back later, beyond what fits in a single conversation., long-term memorylong-term memory, n.: Memory that lasts. For an AI agent, it means information saved outside the conversation — facts, past events, learned procedures — that can be looked up and used again days or months later.