AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

MoDem: Accelerating Visual Model-Based Reinforcement Learning with Demonstrations

Nicklas Hansen, Yixin Lin, Hao Su, Xiaolong Wang, Vikash Kumar, Aravind Rajeswaran

ICLR 2023 · Reinforcement learning › Visual and representation RL · approach: Latent-space world models · 8 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
Use MoDem's three-phase demonstration framework with TD-MPCTD-MPC on Adroit, Meta-World, and DMControl · 21 visual control taskssuccess rate or episode return: 160%-250% more successfulImproved
Add policy pretraining by behavior cloning (ablation)MoDem · Adroitsuccess rateImproved
Seed world-model learning with rollouts from the pretrained BC policy rather than random interactions (ablation)MoDem · Adroitsuccess rateImproved
Oversample demonstrations during interactive learning instead of merely appending them to the buffer (ablation)MoDem · Adroitsuccess rateImproved
Append demonstrations to TD-MPC's replay buffer without MoDem's targeted phases and oversampling (ablation)TD-MPC · Adroitsuccess rateNo clear effect
Increase the number of demonstrations (ablation)MoDem · Adroitsuccess rateImproved
Use a single demonstration instead of five (ablation)MoDem · Adroitsuccess rateMixed
Vary how much interaction data is collected using the pretrained policy (ablation)MoDem · Adroitsuccess rateNo clear effect
Add random image shift augmentation to end-to-end representation learning (ablation)MoDem · Adroitsuccess rateImproved
Anneal demonstration sampling from 75% to 25% instead of keeping it at 25% (ablation)MoDem · Adroitsuccess rateNo clear effect
Use oracle-policy rather than human demonstrations (ablation)MoDem · Adroitsuccess rateMixed
Learn the visual representation end-to-end rather than using frozen R3M features (ablation)MoDem · Adroitsuccess rateImproved

Later papers that compared with this method

3 later accepted papers report MoDem 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