Implicit Behavioral Cloning
This addresses the problem of improving robot policy learning from demonstrations for researchers and practitioners, offering a novel approach that is incremental in method but shows strong gains.
The paper tackles robot policy learning by showing that implicit models, particularly energy-based models, outperform explicit models like Mean Square Error or Mixture Density in behavioral cloning across various tasks, achieving competitive or superior results on the D4RL benchmark and enabling real-world robots to learn complex, precise behaviors from human demonstrations.
We find that across a wide range of robot policy learning scenarios, treating supervised policy learning with an implicit model generally performs better, on average, than commonly used explicit models. We present extensive experiments on this finding, and we provide both intuitive insight and theoretical arguments distinguishing the properties of implicit models compared to their explicit counterparts, particularly with respect to approximating complex, potentially discontinuous and multi-valued (set-valued) functions. On robotic policy learning tasks we show that implicit behavioral cloning policies with energy-based models (EBM) often outperform common explicit (Mean Square Error, or Mixture Density) behavioral cloning policies, including on tasks with high-dimensional action spaces and visual image inputs. We find these policies provide competitive results or outperform state-of-the-art offline reinforcement learning methods on the challenging human-expert tasks from the D4RL benchmark suite, despite using no reward information. In the real world, robots with implicit policies can learn complex and remarkably subtle behaviors on contact-rich tasks from human demonstrations, including tasks with high combinatorial complexity and tasks requiring 1mm precision.