AI Paper Atlas

Research map / Reinforcement learning / Imitation learning

Multi-Modal Inverse Constrained Reinforcement Learning from a Mixture of Demonstrations

Guanren Qiao, Guiliang Liu, Pascal Poupart, zhiqiang xu

NeurIPS 2023 · Reinforcement learning › Imitation learning · approach: Theory of inverse 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
add contrastive estimation (InfoNCE) to policy update (MMICRL-LD -> MMICRL) (ablation)MMICRL · Blocked Half-Cheetah agent z0feasible cumulative rewards: 4.32E+3 -> 6.12E+3Improved
add contrastive estimation to policy update (ablation)MMICRL · Blocked Half-Cheetahconstraint violation rate: 33%±24% / 34%±24% -> 0%±0% / 0%±0%Improved
add contrastive estimation to policy update (ablation)MMICRL · Blocked Ant agent z0feasible cumulative rewards: 1.82E+4/ 2.21E+4 -> 2.13E+4 / 2.17E+4Improved
add contrastive estimation to policy update (ablation)MMICRL · Blocked Antconstraint violation rate: 0%±0% / 0%±0% -> 0%±0% / 0%±0%No clear effect
add contrastive estimation to policy update (ablation)MMICRL · Blocked Swimmer agent z0feasible cumulative rewards: 2.66E+2 -> 4.07E+2Improved
add contrastive estimation to policy update (ablation)MMICRL · Blocked Swimmerconstraint violation rate: 71%±16% / 34%±23% -> 55%±23% / 28%±19%Improved
add contrastive estimation to policy update (ablation)MMICRL · Blocked Walkerfeasible cumulative rewards: 9.02E+2 / 5.12E+2 -> 8.98E+2 / 1.53E+3Mixed
add contrastive estimation to policy update (ablation)MMICRL · Blocked Walkerconstraint violation rate: 52%±25% / 50%±25% -> 31%±22% / 25%±22%Improved
replace trajectory-level flow density identifier with state-action discriminator (InfoGAIL-ICRL)MMICRL · Blocked Half-Cheetah agent z0feasible cumulative rewards: 6.12E+3 -> 2.22E+2Hurt
remove agent identification (MEICRL, single unified constraint)MMICRL · Blocked Half-Cheetahconstraint violation rate: 0%±0% / 0%±0% -> 100%±0% / 50%±25%Hurt
remove agent identification (MEICRL)MMICRL · Blocked Walkerconstraint violation rate: 31%±22% / 25%±22% -> 100%±0% / 100%±0%Hurt
remove agent identification (B2CL/MEICRL)MMICRL · Gridworldconstraint recoveryHurt

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