Corpus ID: 226226483

The MAGICAL Benchmark for Robust Imitation

  title={The MAGICAL Benchmark for Robust Imitation},
  author={S. Toyer and Rohin Shah and Andrew Critch and Stuart J. Russell},
Imitation Learning (IL) algorithms are typically evaluated in the same environment that was used to create demonstrations. This rewards precise reproduction of demonstrations in one particular environment, but provides little information about how robustly an algorithm can generalise the demonstrator's intent to substantially different deployment settings. This paper presents the MAGICAL benchmark suite, which permits systematic evaluation of generalisation by quantifying robustness to… Expand
What Matters in Learning from Offline Human Demonstrations for Robot Manipulation
This study analyzes the most critical challenges when learning from offline human data for manipulation and highlights opportunities for learning from human datasets, such as the ability to learn proficient policies on challenging, multi-stage tasks beyond the scope of current reinforcement learning methods. Expand
XIRL: Cross-embodiment Inverse Reinforcement Learning
This work presents a self-supervised method for Cross-embodiment Inverse Reinforcement Learning (XIRL) that leverages temporal cycle-consistency constraints to learn deep visual embeddings that capture task progression from offline videos of demonstrations across multiple expert agents, each performing the same task differently due to embodiment differences. Expand
The Medkit-Learn(ing) Environment: Medical Decision Modelling through Simulation
The Medkit-Learn(ing) Environment, a publicly available Python package providing simple and easy access to high-fidelity synthetic medical data, is presented, providing a standardised way to compare algorithms in a realistic medical setting and enabling systematic evaluation of algorithms’ robustness against specific challenges prevalent in healthcare. Expand
Multi-Task Learning with Sequence-Conditioned Transporter Networks
Enabling robots to solve multiple manipulation tasks has a wide range of industrial applications. While learning-based approaches enjoy flexibility and generalizability, scaling these approaches toExpand


Simitate: A Hybrid Imitation Learning Benchmark
A benchmarking suite that aims at fostering comparability and reproducibility supports the development of imitation learning approaches and proposes and integrates evaluation metrics on assessing the quality of effect and trajectory of the imitation performed in simulation. Expand
Learning a Prior over Intent via Meta-Inverse Reinforcement Learning
This work exploits the insight that demonstrations from other tasks can be used to constrain the set of possible reward functions by learning a "prior" that is specifically optimized for the ability to infer expressive reward functions from limited numbers of demonstrations. Expand
One-Shot Imitation Learning
A meta-learning framework for achieving one-shot imitation learning, where ideally, robots should be able to learn from very few demonstrations of any given task, and instantly generalize to new situations of the same task, without requiring task-specific engineering. Expand
Task-Embedded Control Networks for Few-Shot Imitation Learning
Task-Embedded Control Networks are introduced, which employ ideas from metric learning in order to create a task embedding that can be used by a robot to learn new tasks from one or more demonstrations, and which surpass the performance of a state-of-the-art method when using only visual information from each demonstration. Expand
Meta-Inverse Reinforcement Learning with Probabilistic Context Variables
This work proposes a deep latent variable model that is capable of learning rewards from unstructured, multi-task demonstration data, and critically, uses this experience to infer robust rewards for new, structurally-similar tasks from a single demonstration. Expand
Behavioral Cloning from Observation
This work proposes a two-phase, autonomous imitation learning technique called behavioral cloning from observation (BCO), that allows the agent to acquire experience in a self-supervised fashion to develop a model which is then utilized to learn a particular task by observing an expert perform that task without the knowledge of the specific actions taken. Expand
RLBench: The Robot Learning Benchmark & Learning Environment
This large-scale benchmark aims to accelerate progress in a number of vision-guided manipulation research areas, including: reinforcement learning, imitation learning, multi-task learning, geometric computer vision, and in particular, few-shot learning. Expand
Learning Robust Rewards with Adversarial Inverse Reinforcement Learning
It is demonstrated that AIRL is able to recover reward functions that are robust to changes in dynamics, enabling us to learn policies even under significant variation in the environment seen during training. Expand
Robot Programming by Demonstration
Drawing on findings from robot control, human-robot interaction, applied machine learning, artificial intelligence, and developmental and cognitive psychology, the book contains a large set of didactic and illustrative examples. Expand
Quantifying Generalization in Reinforcement Learning
It is shown that deeper convolutional architectures improve generalization, as do methods traditionally found in supervised learning, including L2 regularization, dropout, data augmentation and batch normalization. Expand