AI Paper Atlas

Research map / Reinforcement learning / Offline RL

RORL: Robust Offline Reinforcement Learning via Conservative Smoothing

Rui Yang, Chenjia Bai, Xiaoteng Ma, Zhaoran Wang, Chongjie Zhang, Lei Han

NeurIPS 2022 · Reinforcement learning › Offline RL · approach: Simple practical offline RL · 10 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 conservative smoothing for perturbed states and uncertainty-based OOD value penaltiesSAC-10, producing RORL · D4RL Gym tasksnormalized average return: 50.8 -> 85.7Improved
Add conservative smoothing and OOD value penaltiesPBRL · D4RL Gym tasksnormalized average return: 74.4 -> 85.7Improved
Add conservative smoothing and OOD value penaltiesEDAC-10 · D4RL Gym tasksnormalized average return: 71.2 -> 85.7Improved
Add conservative smoothing constraintsCQL · walker-medium-v2 under adversarial observation perturbationsnormalized returnImproved
Remove the OOD loss (ablation)RORL · walker2d-medium-v2 under adversarial observation attacksnormalized returnHurt
Remove policy smoothing (ablation)RORL · walker2d-medium-v2 under adversarial observation attacksnormalized returnHurt
Remove Q smoothing (ablation)RORL · walker2d-medium-v2 under adversarial observation attacksnormalized returnHurt
Use adversarially perturbed observations during evaluationRORL versus EDAC and SAC-10 · HalfCheetah-medium-v2, Walker2d-medium-v2, and Hopper-medium-v2normalized returnImproved
Use mixed-order rather than vanilla zero-order optimization for attacksAdversarial evaluation of ensemble-based offline RL · HalfCheetah-medium-v2, Walker2d-medium-v2, and Hopper-medium-v2normalized returnHurt

Later papers that compared with this method

5 later accepted papers report RORL as a baseline in their results tables; 4 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