AI Paper Atlas

Research map / Multi-agent systems and games / Games and equilibria

Algorithmic Improvements for Deep Reinforcement Learning Applied to Interactive Fiction

Vishal Jain, William Fedus, Hugo Larochelle, Doina Precup, Marc G. Bellemare

AAAI 2020 · Multi-agent systems and games › Games and equilibria · approach: Learning in Markov games · 17 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
Add score contextualisation (separate value-function heads keyed by cumulative reward)LSTM-DRQN · SaladWorld Levels 1–3fraction of subtasks completedImproved
Add score contextualisation and masking based on predicted admissibilityLSTM-DRQN · SaladWorld Level 3fraction of subtasks completedImproved
Add score contextualisation and masking based on predicted admissibilityLSTM-DRQN · SaladWorld Levels 4–7learning speedImproved
Use action gating without score contextualisation (ablation)LSTM-DRQN · SaladWorld Levels 2–7fraction of subtasks completedNo clear effect
Use masking rather than dropout or CQLH for action gating (ablation)Score-contextualised LSTM-DRQN · SaladWorld Level 3fraction of subtasks completedImproved
Replace learned admissibility estimates with the oracle admissible-action set (ablation)Score-contextualised LSTM-DRQN · SaladWorldlearning speedImproved
Use the score-contextualising agent without information-gathering actionsScore-contextualised LSTM-DRQN · Zork IscoreImproved
Remove prioritized sampling (ablation)LSTM-DRQN · Zork IscoreHurt
Remove the infrequent look action (ablation)LSTM-DRQN · Zork IscoreHurt
Replace CQLH with alternate CQLH, which omits the unchanged-state update term (ablation)CQLH agent · Zork IscoreHurt
Use one value-function head instead of score-specific heads (ablation)Score-contextualised LSTM-DRQN · SaladWorldlearning speedHurt

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