PEMIRL

Reported on 4 benchmarks across 1 task · 1 paper · 4 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Robots4 results

MuJoCo GamesonAnt
Average Return· 2019-09-20
846.18
best: 4362.9 (IQ-Learn)
SOTA
Meta-Inverse Reinforcement Learning with Probabilistic Context Variables arXiv:1909.09314
MuJoCo GamesonSweeper
Average Return· 2019-09-20
-74.17
SOTA
Meta-Inverse Reinforcement Learning with Probabilistic Context Variables arXiv:1909.09314
MuJoCo GamesonSawyer Pusher
Average Return· 2019-09-20
-27.16
SOTA
Meta-Inverse Reinforcement Learning with Probabilistic Context Variables arXiv:1909.09314
MuJoCo GamesonPoint Maze
Average Return· 2019-09-20
-7.37
SOTA
Meta-Inverse Reinforcement Learning with Probabilistic Context Variables arXiv:1909.09314