List your company

ResearchFormerly WizWand

DSRL

Benchmarks

TaskDatasetSOTA resultTrendResults

Safe Reinforcement Learning

DSRL EasyMean

324.41Reward

7

Constrained Offline Reinforcement Learning

DSRL CarCircle1

0.73Normalized Return

7

Constrained Offline Reinforcement Learning

DSRL CarGoal1

0.79Normalized Return

7

Constrained Offline Reinforcement Learning

DSRL PointCircle1

0.86Normalized Return

7

Constrained Offline Reinforcement Learning

DSRL PointGoal1

0.74Normalized Return

7

Constrained Offline Reinforcement Learning

DSRL HalfCheetahVelocity

105Normalized Return

7

Constrained Offline Reinforcement Learning

DSRL Walker2dVelocity

0.8Normalized Return

7

Constrained Offline Reinforcement Learning

DSRL HopperVelocity

0.81Normalized Return

7

Offline Safe Reinforcement Learning

DSRL Mean

270.45Reward

4

Offline Safe Reinforcement Learning

DSRL HardDense

243.63Reward

4

Offline Safe Reinforcement Learning

DSRL HardMean

253.58Reward

4

Offline Safe Reinforcement Learning

DSRL HardSparse

257.98Reward

4

Offline Safe Reinforcement Learning

DSRL MediumDense

237.75Reward

4

Offline Safe Reinforcement Learning

DSRL MediumMean

236.57Reward

4

Offline Safe Reinforcement Learning

DSRL MediumSparse

242.75Reward

4

Offline Safe Reinforcement Learning

DSRL EasyDense

316.47Reward

4

Offline Safe Reinforcement Learning

DSRL EasySparse

326.06Reward

4

Safe Reinforcement Learning

DSRL Average across 9 tasks

270.45Reward

3

Safe Reinforcement Learning

DSRL HardDense

243.63Reward

3

Safe Reinforcement Learning

DSRL HardMean

253.58Reward

3

Safe Reinforcement Learning

DSRL HardSparse

257.98Reward

3

Safe Reinforcement Learning

DSRL MediumDense

237.75Reward

3

Safe Reinforcement Learning

DSRL MediumMean

236.57Reward

3

Safe Reinforcement Learning

DSRL MediumSparse

242.75Reward

3

Safe Reinforcement Learning

DSRL EasyDense

316.47Reward

3