AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Minigrid & Miniworld: Modular & Customizable Reinforcement Learning Environments for Goal-Oriented Tasks

Maxime Chevalier-Boisvert, Bolun Dai, Mark Towers, Rodrigo De Lazcano Perez-Vicente, Lucas Willems, Salem Lahlou, Suman Pal, Pablo Samuel Castro, J K Terry

NeurIPS 2023 · Reinforcement learning › Visual and representation RL · approach: Scalable RL systems and environments · 16 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
add transferred critic network weights (not frozen) from Minigrid (ablation)PPO on miniworld-gotoobj-env · Miniworld GoToObjtransfer improvement (%): 3.993Improved
also transfer actor weights alongside critic and mission (ablation)PPO on miniworld-gotoobj-env · Miniworld GoToObjtransfer improvement (%): 3.207 -> -9.494Hurt
freeze transferred weights (critic+mission) (ablation)PPO on miniworld-gotoobj-env · Miniworld GoToObjtransfer improvement (%): 3.207 -> 0.001Hurt
freeze transferred critic weights (ablation)PPO on miniworld-gotoobj-env · Miniworld GoToObjtransfer improvement (%): 3.993 -> 2.760Hurt
transfer actor weights only (ablation)PPO on miniworld-gotoobj-env · Miniworld GoToObjtransfer improvement (%): -8.881Hurt
pre-train humans on Minigrid before Miniworldhuman subjects on Miniworld FourRooms · Miniworld FourRoomsmean rewardNo 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