AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Reinforcement Learning in POMDPs With Memoryless Options and Option-Observation Initiation Sets

Denis Steckelmacher, Diederik Roijers, Anna Harutyunyan, Peter Vrancx, Hélène Plisnier, Ann Nowé

AAAI 2018 · Reinforcement learning › Visual and representation RL · approach: In-context and adaptive RL · 13 citations (OpenAlex)

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
Condition option initiation on the previously executed optionOptions in Object Gathering · Object Gatheringcumulative reward per episodeImproved
Use LSTM memory over options instead of OOIsObject Gathering agent · Object Gatheringepisodes needed to learn a good policyHurt
Condition option initiation on the previously executed optionOptions in Modified DuplicatedInput · Modified DuplicatedInputcumulative reward per episodeImproved
Use standard initiation sets instead of OOIs (ablation)Two-option agent · Modified DuplicatedInputcumulative reward per episodeHurt
Use randomly sampled option initiation setsModified DuplicatedInput agent with learned option policies · Modified DuplicatedInputcumulative reward per episodeImproved
Use LSTM memory over options instead of OOIsModified DuplicatedInput agent · Modified DuplicatedInputcumulative reward per episodeHurt
Reduce the option set from 14 options to 8 or 4 while retaining OOIs (ablation)TreeMaze agent · TreeMazecumulative reward per episodeHurt
Use OOIs rather than standard initiation setsTreeMaze agent with 14 options · TreeMazecumulative reward per episodeImproved
Use LSTM memory over options instead of OOIsTreeMaze agent · TreeMazeepisodes to learn the optimal policy: more than 100K episodesHurt

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