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

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. For example, a commonly used meta-reinforcement learning benchmark uses different running velocities for a simulated robot as different tasks. When policies are meta-trained on such narrow task distributions, they cannot possibly generalize to more quickly acquire entirely new tasks. Therefore, if the aim of these methods is to enable faster acquisition of entirely new behaviors, we must evaluate them on task distributions that are sufficiently broad to enable generalization to new behaviors. In this paper, we propose an open-source simulated benchmark for meta-reinforcement learning and multi-task learning consisting of 50 distinct robotic manipulation tasks. Our aim is to make it possible to develop algorithms that generalize to accelerate the acquisition of entirely new, held-out tasks. We evaluate 7 state-of-the-art meta-reinforcement learning and multi-task learning algorithms on these tasks. Surprisingly, while each task and its variations (e.g., with different object positions) can be learned with reasonable success, these algorithms struggle to learn with multiple tasks at the same time, even with as few as ten distinct training tasks. Our analysis and open-source environments pave the way for future research in multi-task learning and meta-learning that can enable meaningful generalization, thereby unlocking the full potential of these methods.

PDF Abstract


Introduced in the Paper:

Meta-World Benchmark

Results from the Paper

Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Meta-Learning ML10 MAML Meta-train success rate 25% # 5
Meta-test success rate 36% # 1
Meta-Learning ML10 PEARL Meta-train success rate 42.78% # 4
Meta-test success rate 0% # 4
Meta-Learning ML10 RL^2 Meta-train success rate 50% # 3
Meta-test success rate 10% # 2
Meta-Learning MT50 Multi-task multi-head SAC Average Success Rate 35.85% # 2


No methods listed for this paper. Add relevant methods here