Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning

24 Oct 2019Tianhe YuDeirdre QuillenZhanpeng HeRyan JulianKarol HausmanChelsea FinnSergey Levine

Meta-reinforcement learning algorithms can enable robots to acquire new skills much more quickly, by leveraging prior experience to learn how to learn. However, much of the current research on meta-reinforcement learning focuses on task distributions that are very narrow... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Meta-Learning ML10 MAML Meta-train success rate 25% # 3
Meta-test success rate 36% # 1
Meta-Learning ML10 PEARL Meta-train success rate 42.78% # 2
Meta-test success rate 0% # 4
Meta-Learning ML10 RL^2 Meta-train success rate 50% # 1
Meta-test success rate 10% # 2
Meta-Learning MT50 Multi-task multi-head SAC Average Success Rate 35.85% # 2

Methods used in the Paper


METHOD TYPE
🤖 No Methods Found Help the community by adding them if they're not listed; e.g. Deep Residual Learning for Image Recognition uses ResNet