AI Paper Atlas

Research map / Reinforcement learning / Policy gradient and actor-critic

Temporal Difference Learning for Model Predictive Control

Nicklas A Hansen, Hao Su, Xiaolong Wang

ICML 2022 · Reinforcement learning › Policy gradient and actor-critic · approach: Model-based RL with guarantees · 26 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 TD-MPC instead of DrQDMControl image-based control · Finger Spin, DMControl 100kreturn: 901 \scriptstyle{\pm 104} -> 943 \scriptstyle{\pm 59}Improved
Use TD-MPC instead of DrQDMControl image-based control · Walker Walk, DMControl 100kreturn: 612 \scriptstyle{\pm 164} -> 577 \scriptstyle{\pm 208}Hurt
Use TD-MPC instead of DrQDMControl image-based control · Cheetah Run, DMControl 100kreturn: 344 \scriptstyle{\pm 67} -> 222 \scriptstyle{\pm 88}Hurt
Add latent state consistency loss rather than using no regularization (ablation)TD-MPC · DMControl, 15 state-based tasksreturnImproved
Use latent state consistency rather than reconstruction or contrastive regularization (ablation)TD-MPC · DMControl, 15 state-based tasksreturnMixed
Add latent state consistency loss (ablation)TD-MPC · DMControl state-based tasksreturnImproved
Learn a representation instead of using an identity mapping and state-space prediction (ablation)TD-MPC · DMControl state-based tasksreturnMixed
Add latent state consistency loss (ablation)TD-MPC · DMControl state-based tasksreturnMixed
Use TD-MPC instead of SACWalker Walk · Walker Walktime to solve (h): $0.41$ -> $0.47$Hurt
Use TD-MPC instead of SACHumanoid Stand · Humanoid Standtime to solve (h): $9.31$ -> $9.39$Hurt
Increase planning computational budgetTD-MPC · Quadruped WalkreturnImproved
Reduce planning iterations during inferenceTD-MPC · DMControl tasksreturn: 50%No clear effect

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