Strategic use of data is vital for progress in science, commerce, and even politics, but at the same time, citizens are demanding more responsible, respectful use of personal data. Internet… Read More »MIT launches new data privacy-focused initiative
Cross-posted from the DeepMind Safety blog.
In many reinforcement learning problems the objective is too complex to be specified procedurally, and a reward function must instead be learned from user data. However, how can you tell if a learned reward function actually captures user preferences? Our method, Equivalent-Policy Invariant Comparison (EPIC), allows one to evaluate a reward function by computing how similar it is to other reward functions. EPIC can be used to benchmark reward learning algorithms by comparing learned reward functions to a ground-truth reward. It can also be used to validate learned reward functions prior to deployment, by comparing them against reward functions learned via different techniques or data sources.
Figure 1: EPIC compares reward functions $R_a$ and $R_b$ by first mapping them to canonical representatives and then computing the Pearson distance between the canonical representatives on a coverage distribution $mathcal{D}$. Canonicalization removes the effect of potential shaping, and Pearson distance is invariant to positive affine transformations.
Model-based reinforcement learning (MBRL) is a variant of the iterative learning framework, reinforcement learning, that includes a structured component of the system that is solely optimized to model the environment dynamics. Learning a model is broadly motivated from biology, optimal control, and more – it is grounded in natural human intuition of planning before acting. This intuitive grounding, however, results in a more complicated learning process. In this post, we discuss how model-based reinforcement learning is more susceptible to parameter tuning and how AutoML can help in finding very well performing parameter settings and schedules. Below, left is the expected behavior of an agent maximizing velocity on a “Half Cheetah” robotic task, and to the right is what our paper with hyperparameter tuning finds.
Read More »The Importance of Hyperparameter Optimization for Model-based Reinforcement Learning
Whatever business a company may be in, software plays an increasingly vital role, from managing inventory to interfacing with customers. Software developers, as a result, are in greater demand than… Read More »Toward deep-learning models that can reason about code more like humans
Over the past decade, hospitals and other health care providers have put massive amounts of time and energy into adopting electronic health care records, turning hastily scribbled doctors’ notes into… Read More »One-stop machine learning platform turns health care data into insights
Melanoma is a type of malignant tumor responsible for more than 70 percent of all skin cancer-related deaths worldwide. For years, physicians have relied on visual inspection to identify suspicious… Read More »An artificial intelligence tool that can help detect melanoma
In recent years, robots have gained artificial vision, touch, and even smell. “Researchers have been giving robots human-like perception,” says MIT Associate Professor Fadel Adib. In a new paper, Adib’s… Read More »A robot that senses hidden objects