DeepAI AI Chat
Log In Sign Up

Relay Policy Learning: Solving Long-Horizon Tasks via Imitation and Reinforcement Learning

by   Abhishek Gupta, et al.

We present relay policy learning, a method for imitation and reinforcement learning that can solve multi-stage, long-horizon robotic tasks. This general and universally-applicable, two-phase approach consists of an imitation learning stage that produces goal-conditioned hierarchical policies, and a reinforcement learning phase that finetunes these policies for task performance. Our method, while not necessarily perfect at imitation learning, is very amenable to further improvement via environment interaction, allowing it to scale to challenging long-horizon tasks. We simplify the long-horizon policy learning problem by using a novel data-relabeling algorithm for learning goal-conditioned hierarchical policies, where the low-level only acts for a fixed number of steps, regardless of the goal achieved. While we rely on demonstration data to bootstrap policy learning, we do not assume access to demonstrations of every specific tasks that is being solved, and instead leverage unstructured and unsegmented demonstrations of semantically meaningful behaviors that are not only less burdensome to provide, but also can greatly facilitate further improvement using reinforcement learning. We demonstrate the effectiveness of our method on a number of multi-stage, long-horizon manipulation tasks in a challenging kitchen simulation environment. Videos are available at


page 1

page 7

page 13


Learning to Generalize Across Long-Horizon Tasks from Human Demonstrations

Imitation learning is an effective and safe technique to train robot pol...

CRISP: Curriculum inducing Primitive Informed Subgoal Prediction for Hierarchical Reinforcement Learning

Hierarchical reinforcement learning is a promising approach that uses te...

Goal-Conditioned Imitation Learning using Score-based Diffusion Policies

We propose a new policy representation based on score-based diffusion mo...

Seeing All the Angles: Learning Multiview Manipulation Policies for Contact-Rich Tasks from Demonstrations

Learned visuomotor policies have shown considerable success as an altern...

Chain-of-Thought Predictive Control

We study generalizable policy learning from demonstrations for complex l...

Divide Conquer Imitation Learning

When cast into the Deep Reinforcement Learning framework, many robotics ...

Code Repositories


pointMass pybullet RL environment for simple experiments

view repo