List your company
ResearchFormerly WizWand

Reinforcement Learning on LunarLander v2

2,292Final ReturnAdvantage-weighting
-173.216466.7921,106.81,746.808Oct 1, 2019Nov 7, 2020Dec 16, 2021Jan 23, 2023Mar 2, 2024Apr 9, 2025May 18, 2026
Updated 5mo ago

Evaluation results

MethodLinks
Advantage-weightingSource=Peng et al.2020.122,292518,153
PPOAlgorithm=PPO, Policy Type=Neural2026.05283.11—
Deep Q NetworkSource=Xinly Yu2020.12278.23518,153
Oblique DTCriteria=Best Score2020.12272.14118.9
Deep Q NetworkSource=Sigve Rokenes2020.12266121,000,000
Oblique DTCriteria=Best M2020.12262.1886.9
DiPRLAlgorithm=DiPRL, Maximal Depth=62026.05260.21—
Shallow NNSource=Malagon et al.2020.12258.877.6
DTSemNetsAlgorithm=DTSemNets2026.05257.61—
π-PRLAlgorithm=π-PRL, Policy Stage=final fine-tuned policy, Maximal Depth=62026.05257.21—
Actor CriticSource=Nikhil Barhate2020.12254.584,337.3
Value-differenceSource=Xu et al.2020.12248.221632,620.2
πdisc.-PRLAlgorithm=π-PRL, Policy Stage=discretized policy before fine-tuning, Maximal Depth=62026.05239.9—
πcont.-PRLAlgorithm=π-PRL, Policy Stage=relaxed policy before discretization, Maximal Depth=62026.05235.72—
AWR2019.10229—
Deep Q NetworkSource=Ash Bellet2020.12225.791,295,307.1
Soft Actor CriticSource=Keavan2020.12217.92210,733.2
Soft Q NetworkSource=liu2020.12217.09647,691.1
Proximal Policy Opt.Source=Daniel Barbosa2020.12201.471,673
Deep Q NetworkSource=Ollie Graham2020.12201.4630,878.1
Deep Q NetworkSource=Udacity2020.12201.4630,878.1
Deep Q NetworkSource=Sanket Thakur2020.12200.65259,285.8
Deep Q NetworkSource=Mahmood2020.12200.3237,079.7
Dueling Deep Q N.Source=Ruslan2020.12200.2230,878.1
RWR2019.10185—
VIPER (PPO)Algorithm=VIPER, Oracle Usage=PPO, Maximal Depth=62026.05164.33—
NLDT*Source=Dhebar et al., Depth=32020.12132.83136.7
PPO2019.10121—
TRPO2019.10104—
Rule ListSource=Silva et al.2020.12-78.489
Oblique DTCriteria=Mean2020.12—123.3439