AI Paper Atlas

Research map / Reinforcement learning / MDPs and planning

RUDDER: Return Decomposition for Delayed Rewards

Jose A. Arjona-Medina, Michael Gillhofer, Michael Widrich, Thomas Unterthiner, Johannes Brandstetter, Sepp Hochreiter

NeurIPS 2019 · Reinforcement learning › MDPs and planning · approach: Average-reward and regularized MDPs · 105 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 return decomposition and reward redistribution to PPOPPO · Bowlingaverage score: 56 -> 192Improved
Add return decomposition and reward redistribution to PPOPPO · Solarisaverage score: 616 -> 1,827Improved
Add return decomposition and reward redistribution to PPOPPO · Ventureaverage score: 820 -> 1,350Improved
Add return decomposition and reward redistribution to PPOPPO · Seaquestaverage score: 1,616 -> 4,770Improved
Redistribute delayed rewards using return decompositionRUDDER · Grid Worldlearning time to 90% of maximal expected returnImproved
Redistribute delayed rewards using return decompositionRUDDER · The Choicelearning time to 90% of maximal expected returnImproved
Redistribute delayed rewards using return decompositionRUDDER · Trace-Backlearning time to 90% of maximal expected returnImproved
Use RUDDER instead of the PPO baselinePPO on Atari · 32 Atari gameslearning speedImproved
Use RUDDER instead of the PPO baselinePPO on Atari · Atari gamesaverage score in the last 10 training gamesMixed

Later papers that compared with this method

2 later accepted papers report Rudder as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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