Our new X account is live! Follow @wizwand_team for updates
Search any
task
Feedback
Search any
task
SOTA Multi-task reinforcement learning benchmarks and papers with code | Wizwand
Our new X account is live! Follow @wizwand_team for updates
Home
/
Tasks
Multi-task reinforcement learning
Benchmarks
Dataset Name
SOTA Method
Dataset Name
SOTA Method
Metric
Trend
Results
Last Updated
Meta-World MT10 v1 (Fixed)
MT-MH-SAC
Success Rate
88
12
4d ago
Metaworld MT10 v2 (train/eval)
FAMO
Time
4.2
11
4d ago
Meta-World MT10 v1 (train test)
Nash-MTL
Average Success
91
9
4d ago
Meta-World MT50 (MT50-rand) V2 (Near-optimal)
MTDIFF-P-ONEHOT
Avg Success Rate
61.32
8
4d ago
Meta-World MT50 v1 (Fixed)
Soft Modularization (Deep)
Success Rate
60
8
4d ago
DMLab-30 (test)
PopArt-IMPALA
Mean Capped Human Score
72.8
8
4d ago
Meta-World MT50-rand V2 (Sub-optimal)
MTDIFF-P-ONEHOT
Average Success Rate
48.94
6
4d ago
Meta-World MT50 Conditioned v1
Soft Modularization (Deep)
Average Success Rate
61
6
4d ago
Meta-World MT10 Conditioned v1
Soft Modularization (Shallow)
Average Success Rate
71.8
6
4d ago
DMLab-30 Multi-task Standard
LASER: Shared Experience Replay
Mean-Capped Human-Normalized Score
81.7
4
4d ago
Atari-57 unclipped
PopArt-IMPALA
Median Human Normalised Score
10,700
4
4d ago
Atari-57 clipped
PopArt-IMPALA
Median Human Normalized Score
110.7
4
4d ago
DmLab-30 (train)
PopArt-IMPALA
Mean capped human normalised score
0.735
2
4d ago
Meta-World
-
-
0
4d ago
Showing 14 of 14 rows
25 / page
50 / page
100 / page
1
Search any
task
Search any
task
Terms of Service
FAQs
