AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

RePo: Resilient Model-Based Reinforcement Learning by Regularizing Posterior Predictability

Chuning Zhu, Max Simchowitz, Siri Gadipudi, Abhishek Gupta

NeurIPS 2023 · Reinforcement learning › Visual and representation RL · approach: Robust visual encoders for RL · 1 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
replace reconstruction-based Dreamer with RePo posterior-predictability objectivevisual model-based RL · Lazy TurtleBotsuccess rate (%): 0.0\% -> 62.5\%Improved
replace reconstruction-based Dreamer with RePovisual model-based RL · Lazy TurtleBotreturn: -61.7 -> -24.3Improved
add a scoreboard distractor showing cumulative reward to the observation (ablation)RePo · Distracted DMC Walker Walkepisode return: 868.72 -> 872.86No clear effect
replace support-matching constraint with distribution matching for test-time adaptation (ablation)RePo test-time adaptation · Walker Stand, Walker Walk, Cheetah Run (static to distracted)adaptation performanceHurt
remove calibration (paired) examples from adaptation (ablation)RePo test-time adaptation · Walker Stand, Walker Walk, Cheetah Runadaptation performanceHurt
add dynamics consistency (ILA) to distribution-matching adaptationtest-time adaptation · Walker Stand, Walker Walk, Cheetah Runadaptation performanceNo clear effect
use calibration alone for adaptationtest-time adaptation · Walker Stand, Walker Walk, Cheetah Runadaptation performanceHurt
vary information bottleneck KL target epsilon (too small) (ablation)RePo · Distracted DMC Walker Walkreward loss / returnHurt
vary information bottleneck KL target epsilon (too large) (ablation)RePo · Distracted DMC Walker WalkreturnHurt
increase learning rate of Lagrange multiplier beta (too high) (ablation)RePo · Distracted DMC Walker WalkreturnHurt
lower learning rate of Lagrange multiplier beta (too low) (ablation)RePo · Distracted DMC Walker WalkreturnHurt
increase KL balancing parameter (train prior more) to a moderate level (ablation)RePo · Distracted DMC Walker WalkreturnImproved

Later papers that compared with this method

3 later accepted papers report RePO as a baseline in their results tables; 3 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