List your company

Reinforcement Learning on LunarLanderContinuous v2

533.6Mean RewardLinear
-11.9424129.6888271.32412.9512Apr 30, 2022Dec 30, 2022Sep 1, 2023May 3, 2024Jan 3, 2025Sep 5, 2025May 8, 2026

Evaluation results

MethodLinks
LinearEpisode Number=1002024.06533.6130.04
LinearEpisode Number=502024.06531.05115.63
LinearEpisode Number=2002024.06513.44129.48
LinearEpisode Number=1502024.06510.13123.56
LinearEpisode Number=5002024.06492.67126.01
LinearEpisode Number=3502024.06479.01124.67
LinearEpisode Number=2502024.06475.43125.81
LinearEpisode Number=3002024.06473.77127.78
LinearEpisode Number=4002024.06458.1131.61
LinearEpisode Number=4502024.06445.52143.65
PPOEpisode Number=502024.06403.56143.06
DDPGEpisode Number=502024.06337.2298.64
TTOptMode size (N)=32022.04290.2924.4
TTOptMode size (N)=2^82022.04286.8721.65
GAMode size (N)=32022.04283.0516.28
DTSemNetNf (Number of features)=8, Na (Number of actions)=2 dim., Height=4, Variant=Top-k2026.05282.49—
CBRLEpisode Number=2502024.06280.3617.19
CBRLEpisode Number=5002024.06280.0917.16
CBRLEpisode Number=3502024.06280.0817.14
CBRLEpisode Number=4002024.06279.5117.67
CBRLEpisode Number=2002024.06279.2418.12
CBRLEpisode Number=3002024.06279.1918.42
CBRLEpisode Number=4502024.06278.9619.22
DTSemNetNf (Number of features)=8, Na (Number of actions)=2 dim., Height=4, Variant=STE2026.05277.24—
Deep RLNf (Number of features)=8, Na (Number of actions)=2 dim., Height=42026.05276.12—
SAC2025.02272.7—
SALSA-RLLatent dimension size (hd)=42025.02268.3—
DGTNf (Number of features)=8, Na (Number of actions)=2 dim., Height=4, Variant=linear2026.05267.9—
SALSA-RLLatent dimension size (hd)=82025.02260.8—
PPOEpisode Number=1002024.06260.08238.84
CBRLEpisode Number=1502024.06258.8431.52
SALSA-RLLatent dimension size (hd)=32025.02257.8—
ICCTNf (Number of features)=8, Na (Number of actions)=2 dim., Height=42026.05255.57—
DSP2025.02251.7—
DDPG2025.02246.2—
SALSA-RLLatent dimension size (hd)=62025.02246.1—
SALSA-RLLatent dimension size (hd)=162025.02242.6—
A2C2025.02227.1—
TD32025.02225.4—
PPO2025.02225.1—
CMAESMode size (N)=2^82022.04221.95133.8
CMAESMode size (N)=32022.04214.5593.79
GAMode size (N)=2^82022.04213.7599.67
PPOEpisode Number=1502024.06188.5121.78
DDPGEpisode Number=1502024.06154.4843.2
DDPGEpisode Number=1002024.06145.0542.29
DDPGEpisode Number=2502024.06143.46112.2
DDPGEpisode Number=2002024.06133.5138.96
DDPGEpisode Number=5002024.06133.266.54
DGTNf (Number of features)=8, Na (Number of actions)=2 dim., Height=4, Variant=scalar2026.05131.92—
CBRLEpisode Number=502024.06128.81276.58
PPOEpisode Number=2502024.06127.2981.82
OPENESMode size (N)=32022.04114.97113.48
PPOEpisode Number=3002024.06109.7279.65
PPOEpisode Number=2002024.06106.87133.97
CBRLEpisode Number=1002024.06101.33262.09
PPOEpisode Number=5002024.0696.5113.1
PPOEpisode Number=4502024.0691.77105.02
PPOEpisode Number=4002024.0675.52111.54
DDPGEpisode Number=3002024.0673.170.24
OPENESMode size (N)=2^82022.0473.08163.33
DDPGEpisode Number=4002024.0670.04120.93
DDPGEpisode Number=4502024.0651.1599.21
PPOEpisode Number=3502024.0645.12140.02
DDPGEpisode Number=3502024.069.0498.49