AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

A Natural Lottery Ticket Winner: Reinforcement Learning with Ordinary Neural Circuits

Ramin Hasani, Mathias Lechner, Alexander Amini, Daniela Rus, Radu Grosu

ICML 2020 · Reinforcement learning › Visual and representation RL · approach: Skill learning and diffusion policies · 10 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 TW-constrained wiring (ONC) instead of random circuits with same size (ablation)ONC with ARS · Half-CheetahreturnImproved
Use TW-constrained wiring (ONC) instead of random circuits with same size (ablation)ONC with ARS · Inverted PendulumreturnImproved
Use TW-constrained wiring (ONC) instead of random circuits with same size (ablation)ONC with ARS · MountaincarreturnImproved
Use ONC (77% sparse TW circuit) instead of fully connected MLP/LSTMONC with ARS · Half-Cheetahreturn: + about 1000 over LSTM (2587.4 vs 1588.9)Improved
Use ONC instead of fully connected MLP/LSTMONC with ARS · Inverted Pendulum and MountaincarreturnNo clear effect
Replace PPO/A2C policy gradient with ARS search-based RL for the ONCONC · Inverted Pendulum and MountainCarreturnNo clear effect
Use TW-constrained wiring in place of random wiring (Algorithm 1 variants) (ablation)Max-flow of sparse random networks · Max-flow rate vs TW (40000 networks)max-flow ratio to TW: ratios 1.15 (Fig 2A) down to 1.01 (Fig 2D); randomly wired networks have higher ratios, so TW is not the maxMixed

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