AI Paper Atlas

Research map / Reinforcement learning / MDPs and planning

Multi-View Reinforcement Learning

Minne Li, Lisheng Wu, Jun WANG, Haitham Bou Ammar

NeurIPS 2019 · Reinforcement learning › MDPs and planning · approach: Average-reward and regularized MDPs · 4 citations (OpenAlex)

Read the paper

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 MV-MB instead of PILCOModel-based Cartpole control · Cartpoleinteractions till success: 240 -> 381 ± 28Hurt
Use MV-MB instead of PILCO-augModel-based Cartpole control · Cartpoleinteractions till success: 320 -> 381 ± 28Hurt
Use MV-MB instead of an MLP dynamics modelModel-based Cartpole control · Cartpoleinteractions till success: 2334 ± 358 -> 381 ± 28Improved
Augment PPO with concatenated observations from multiple viewsModel-free multi-view policy learning · Cartpole and parkingaverage testing returnImproved
Transfer a policy across views using a learned multi-view modelMV-PT · Cartpole, Hopper, RACECAR, and parkingtraining samples to reach good performance: around two orders of magnitudesImproved
Use a single PILCO model on augmented states from all views (ablation)PILCO · Cartpoleinteractions till success: 240 -> 320Hurt

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