Towards Practical Multi-Object Manipulation using Relational Reinforcement Learning

by   Richard Li, et al.

Learning robotic manipulation tasks using reinforcement learning with sparse rewards is currently impractical due to the outrageous data requirements. Many practical tasks require manipulation of multiple objects, and the complexity of such tasks increases with the number of objects. Learning from a curriculum of increasingly complex tasks appears to be a natural solution, but unfortunately, does not work for many scenarios. We hypothesize that the inability of the state-of-the-art algorithms to effectively utilize a task curriculum stems from the absence of inductive biases for transferring knowledge from simpler to complex tasks. We show that graph-based relational architectures overcome this limitation and enable learning of complex tasks when provided with a simple curriculum of tasks with increasing numbers of objects. We demonstrate the utility of our framework on a simulated block stacking task. Starting from scratch, our agent learns to stack six blocks into a tower. Despite using step-wise sparse rewards, our method is orders of magnitude more data-efficient and outperforms the existing state-of-the-art method that utilizes human demonstrations. Furthermore, the learned policy exhibits zero-shot generalization, successfully stacking blocks into taller towers and previously unseen configurations such as pyramids, without any further training.


page 1

page 5

page 6

page 9


Curiosity-Driven Multi-Criteria Hindsight Experience Replay

Dealing with sparse rewards is a longstanding challenge in reinforcement...

Reinforcement Learning for Robotic Manipulation using Simulated Locomotion Demonstrations

Learning robot manipulation policies through reinforcement learning (RL)...

MaMiC: Macro and Micro Curriculum for Robotic Reinforcement Learning

Shaping in humans and animals has been shown to be a powerful tool for l...

Compositional Multi-Object Reinforcement Learning with Linear Relation Networks

Although reinforcement learning has seen remarkable progress over the la...

Curious Exploration via Structured World Models Yields Zero-Shot Object Manipulation

It has been a long-standing dream to design artificial agents that explo...

Curriculum Learning with Hindsight Experience Replay for Sequential Object Manipulation Tasks

Learning complex tasks from scratch is challenging and often impossible ...

Relational Abstractions for Generalized Reinforcement Learning on Symbolic Problems

Reinforcement learning in problems with symbolic state spaces is challen...

Please sign up or login with your details

Forgot password? Click here to reset