AI Paper Atlas

Research map / Multi-agent systems and games / Human-AI and goal-conditioned

Been There, Done That: Meta-Learning with Episodic Recall

ICML 2018 · Multi-agent systems and games › Human-AI and goal-conditioned · approach: Imitation and skill learning · 32 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Add context-keyed episodic memory with gated cell-state reinstatementL2RL · Barcode banditsrewardHelped
Add context-keyed episodic memory with gated cell-state reinstatementL2RL · Omniglot banditsregretHelped
Add context-keyed episodic memory with gated cell-state reinstatementL2RL · Compositional banditsregretHelped
Add context-keyed episodic memory with gated cell-state reinstatementL2RL · Contextual water mazesteps to reach goalHelped
Add context-keyed episodic memory with gated cell-state reinstatementL2RL · Episodic two-step taskrewardHelped
Feed retrieved DND states as LSTM inputs instead of adding them through the reinstatement gate (ablation)epL2RL · Barcode banditsrewardHurt
Compress retrieved states with linear layers or MLPs rather than using gated reinstatement (ablation)epL2RL · bandit tasksrewardMixed
Provide context embeddings as LSTM inputsL2RL · Omniglot banditsrewardHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy