AI Paper Atlas

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

Active Exploration for Learning Symbolic Representations

Garrett Andersen, George Konidaris

NeurIPS 2017 · Multi-agent systems and games › Human-AI and goal-conditioned · approach: Imitation and skill learning

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (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
Use uncertainty-guided active exploration with a Bayesian symbolic model and MCTS instead of random explorationsymbolic representation learning · Asteroidsunobserved symbolic transitions: random exploration required 2-3 times as many option executions to match the proposed methodImproved
Use uncertainty-guided active exploration with a Bayesian symbolic model and MCTS instead of greedy explorationsymbolic representation learning · Asteroidsunobserved symbolic transitions: greedy exploration required 2-3 times as many option executions to match the proposed methodImproved
Use uncertainty-guided active exploration with a Bayesian symbolic model and MCTS instead of random explorationsymbolic representation learning · Treasure Gameunobserved symbolic transitions: random exploration required 2-3 times as many option executions to match the proposed methodImproved
Use uncertainty-guided active exploration with a Bayesian symbolic model and MCTS instead of greedy explorationsymbolic representation learning · Treasure Gameunobserved symbolic transitions: greedy exploration required 2-3 times as many option executions to match the proposed methodImproved
Use uncertainty-guided active exploration instead of random or greedy explorationsymbolic representation learning · Treasure Gametreasure collection frequencyImproved
Use uncertainty-guided active exploration instead of random or greedy explorationsymbolic representation learning · Asteroidsstate-space coverageImproved

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