AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Proximal Distilled Evolutionary Reinforcement Learning

Cristian Bodnar, Ben Day, Pietro Lió

AAAI 2020 · Reinforcement learning › Visual and representation RL · approach: Probabilistic and autonomous RL · 84 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
combine Q-filtered distillation crossover with proximal mutationsERL (PDERL) · Swimmer-v2, HalfCheetah-v2, Hopper-v2, Walker2D-v2, Ant-v2mean reward: 337; 13522; 3397; 5184; 6845Improved
add proximal mutations to Q-filtered distillation crossover (ablation)DERL · Walker2D-v2 and Ant-v2mean reward: 4050 -> 5184; 4911 -> 6845Improved
add proximal mutations to Q-filtered distillation crossover (ablation)DERL · HalfCheetah-v2 and Hopper-v2mean reward: 11362 -> 13522; 2869 -> 3397Mixed
add Q-filtered distillation crossover to proximal mutations (ablation)PERL · Walker2D-v2 and Ant-v2mean reward: 3364 -> 5184; 4528 -> 6845Improved
add Q-filtered distillation crossover to proximal mutations (ablation)PERL · HalfCheetah-v2 and Hopper-v2mean reward: 13668 -> 13522; 3497 -> 3397Hurt
replace n-point crossover with Q-filtered behaviour distillation crossover (ablation)ERL genetic population · Antoffspring fitness relative to best parentImproved
replace Gaussian mutation with proximal mutation (ablation)ERL genetic population · Antoffspring total reward: -187 -> 5496Improved
use distance-based rather than greedy parent selection (ablation)DERL and PDERL · Walker2D-v2mean rewardHurt
use distance-based rather than greedy parent selection (ablation)PDERL · Hopper-v2mean rewardImproved
increase proximal mutation magnitude (ablation)PDERL · policy behaviourbehaviour changeImproved

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