AI Paper Atlas

Research map / Reinforcement learning / MDPs and planning

Learning non-Markovian Decision-Making from State-only Sequences

Aoyang Qin, Feng Gao, Qing Li, Song-Chun Zhu, Sirui Xie

NeurIPS 2023 · Reinforcement learning › MDPs and planning · approach: Average-reward and regularized MDPs · 2 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 LanMDP with context length 3 instead of context length 1 (ablation)LanMDP · CartPolereturn: 500.00$\pm$0.00 -> 500.00$\pm$0.00No clear effect
Use LanMDP with context length 3 instead of context length 1 (ablation)LanMDP · Reacherreturn: -9.00$\pm$0.87 -> -10.91$\pm$0.73Hurt
Use LanMDP with context length 2 instead of context length 1 (ablation)LanMDP · Swimmerreturn: 41.22$\pm$2.67 -> 43.52$\pm$4.31Improved
Use LanMDP with context length 3 instead of context length 1 (ablation)LanMDP · Hopperreturn: 3045.27$\pm$240.45 -> 3051.16$\pm$111.78No clear effect
Use LanMDP with context length 2 instead of context length 1 (ablation)LanMDP · Walker2dreturn: 1753.46$\pm$193.69 -> 1811.77$\pm$369.54No clear effect
Use LanMDP instead of BCLanMDP · CartPolereturn: 474.80$\pm$18.87 -> 500.00$\pm$0.00Improved
Use LanMDP instead of BCLanMDP · Reacherreturn: -8.76$\pm$0.12 -> -9.00$\pm$0.87Hurt
Use LanMDP instead of BCLanMDP · Swimmerreturn: 38.64$\pm$1.76 -> 41.22$\pm$2.67Improved
Use LanMDP instead of BCLanMDP · Hopperreturn: 3083.32$\pm$156.61 -> 3045.27$\pm$240.45No clear effect
Use LanMDP instead of BCLanMDP · Walker2dreturn: 1839.94$\pm$376.87 -> 1753.46$\pm$193.69No clear effect
Replace posterior MCMC sampling with importance sampling (ablation)LanMDP training · Reacher, Swimmer, Hopper, Walker2dtraining time per step: 0.0108/0.0076/0.0014 -> 0.0076/0.0076/0.0014; 0.0100/0.0071/0.0014 -> 0.0071/0.0071/0.0014; 0.0268/0.0170/0.0074 -> 0.01Improved

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