An autonomous experimentation platform in manufacturing is supposedly capable of conducting a sequential search for finding suitable manufacturing conditions for advanced materials by itself or even for discovering new materials with minimal human intervention. The core of the intelligent control of such platforms is the policy directing sequential experiments, namely, to decide where to conduct the next experiment based on what has been done thus far. Such policy inevitably trades off exploitation versus exploration and the current practice is under the Bayesian optimization framework using the expected improvement criterion or its variants. We discuss whether it is beneficial to trade off exploitation versus exploration by measuring the element and degree of surprise associated with the immediate past observation. We devise a surprise-reacting policy using two existing surprise metrics, known as the Shannon surprise and Bayesian surprise. Our analysis shows that the surprise-reacting policy appears to be better suited for quickly characterizing the overall landscape of a response surface or a design place under resource constraints. We argue that such capability is much needed for futuristic autonomous experimentation platforms. We do not claim that we have a fully autonomous experimentation platform, but believe that our current effort sheds new lights or provides a different view angle as researchers are racing to elevate the autonomy of various primitive autonomous experimentation systems.
相關內容
We present CineMPC, an algorithm to autonomously control a UAV-borne video camera in a nonlinear Model Predicted Control (MPC) loop. CineMPC controls both the position and orientation of the camera -- the camera extrinsics -- as well as the lens focal length, focal distance, and aperture -- the camera intrinsics. While some existing solutions autonomously control the position and orientation of the camera, no existing solutions also control the intrinsic parameters, which are essential tools for rich cinematographic expression. The intrinsic parameters control the parts of the scene that are focused or blurred, the viewers' perception of depth in the scene and the position of the targets in the image. CineMPC closes the loop from camera images to UAV trajectory and lens parameters in order to follow the desired relative trajectory and image composition as the targets move through the scene. Experiments using a photo-realistic environment demonstrate the capabilities of the proposed control framework to successfully achieve a full array of cinematographic effects not possible without full camera control.
This paper introduces a probabilistic framework to estimate parameters of an acquisition function given observed human behavior that can be modeled as a collection of sample paths from a Bayesian optimization procedure. The methodology involves defining a likelihood on observed human behavior from an optimization task, where the likelihood is parameterized by a Bayesian optimization subroutine governed by an unknown acquisition function. This structure enables us to make inference on a subject's acquisition function while allowing their behavior to deviate around the solution to the Bayesian optimization subroutine. To test our methods, we designed a sequential optimization task which forced subjects to balance exploration and exploitation in search of an invisible target location. Applying our proposed methods to the resulting data, we find that many subjects tend to exhibit exploration preferences beyond that of standard acquisition functions to capture. Guided by the model discrepancies, we augment the candidate acquisition functions to yield a superior fit to the human behavior in this task.
A central question in multi-agent strategic games deals with learning the underlying utilities driving the agents' behaviour. Motivated by the increasing availability of large data-sets, we develop an unifying data-driven technique to estimate agents' utility functions from their observed behaviour, irrespective of whether the observations correspond to (Nash) equilibrium configurations or to action profile trajectories. Under standard assumptions on the parametrization of the utilities, the proposed inference method is computationally efficient and finds all the parameters that rationalize the observed behaviour best. We numerically validate our theoretical findings on the market share estimation problem under advertising competition, using historical data from the Coca-Cola Company and Pepsi Inc. duopoly.
We consider frequently used scoring rules for right-censored survival regression models such as time-dependent concordance, survival-CRPS, integrated Brier score and integrated binomial log-likelihood, and prove that neither of them is a proper scoring rule. This means that the true survival distribution may be scored worse than incorrect distributions, leading to inaccurate estimation. We prove that, in contrast to these scores, the right-censored log-likelihood is a proper scoring rule, i.e., the highest expected score is achieved by the true distribution. Despite this, modern feed-forward neural-network-based survival regression models are unable to train and validate directly on the right-censored log-likelihood, due to its intractability, and resort to the aforementioned alternatives, i.e., non-proper scoring rules. We therefore propose a simple novel survival regression method capable of directly optimizing log-likelihood using a monotonic restriction on the time-dependent weights, coined SurvivalMonotonic-net (SuMo-net). SuMo-net achieves state-of-the-art log-likelihood scores across several datasets with 20--100$\times$ computational speedup on inference over existing state-of-the-art neural methods, and is readily applicable to datasets with several million observations.
To accumulate knowledge and improve its policy of behaviour, a reinforcement learning agent can learn `off-policy' about policies that differ from the policy used to generate its experience. This is important to learn counterfactuals, or because the experience was generated out of its own control. However, off-policy learning is non-trivial, and standard reinforcement-learning algorithms can be unstable and divergent. In this paper we discuss a novel family of off-policy prediction algorithms which are convergent by construction. The idea is to first learn on-policy about the data-generating behaviour, and then bootstrap an off-policy value estimate on this on-policy estimate, thereby constructing a value estimate that is partially off-policy. This process can be repeated to build a chain of value functions, each time bootstrapping a new estimate on the previous estimate in the chain. Each step in the chain is stable and hence the complete algorithm is guaranteed to be stable. Under mild conditions this comes arbitrarily close to the off-policy TD solution when we increase the length of the chain. Hence it can compute the solution even in cases where off-policy TD diverges. We prove that the proposed scheme is convergent and corresponds to an iterative decomposition of the inverse key matrix. Furthermore it can be interpreted as estimating a novel objective -- that we call a `k-step expedition' -- of following the target policy for finitely many steps before continuing indefinitely with the behaviour policy. Empirically we evaluate the idea on challenging MDPs such as Baird's counter example and observe favourable results.
Bayesian approaches developed to solve the optimal design of sequential experiments are mathematically elegant but computationally challenging. Recently, techniques using amortization have been proposed to make these Bayesian approaches practical, by training a parameterized policy that proposes designs efficiently at deployment time. However, these methods may not sufficiently explore the design space, require access to a differentiable probabilistic model and can only optimize over continuous design spaces. Here, we address these limitations by showing that the problem of optimizing policies can be reduced to solving a Markov decision process (MDP). We solve the equivalent MDP with modern deep reinforcement learning techniques. Our experiments show that our approach is also computationally efficient at deployment time and exhibits state-of-the-art performance on both continuous and discrete design spaces, even when the probabilistic model is a black box.
In real world settings, numerous constraints are present which are hard to specify mathematically. However, for the real world deployment of reinforcement learning (RL), it is critical that RL agents are aware of these constraints, so that they can act safely. In this work, we consider the problem of learning constraints from demonstrations of a constraint-abiding agent's behavior. We experimentally validate our approach and show that our framework can successfully learn the most likely constraints that the agent respects. We further show that these learned constraints are \textit{transferable} to new agents that may have different morphologies and/or reward functions. Previous works in this regard have either mainly been restricted to tabular (discrete) settings, specific types of constraints or assume the environment's transition dynamics. In contrast, our framework is able to learn arbitrary \textit{Markovian} constraints in high-dimensions in a completely model-free setting. The code can be found it: \url{//github.com/shehryar-malik/icrl}.
Meta-reinforcement learning algorithms can enable robots to acquire new skills much more quickly, by leveraging prior experience to learn how to learn. However, much of the current research on meta-reinforcement learning focuses on task distributions that are very narrow. For example, a commonly used meta-reinforcement learning benchmark uses different running velocities for a simulated robot as different tasks. When policies are meta-trained on such narrow task distributions, they cannot possibly generalize to more quickly acquire entirely new tasks. Therefore, if the aim of these methods is to enable faster acquisition of entirely new behaviors, we must evaluate them on task distributions that are sufficiently broad to enable generalization to new behaviors. In this paper, we propose an open-source simulated benchmark for meta-reinforcement learning and multi-task learning consisting of 50 distinct robotic manipulation tasks. Our aim is to make it possible to develop algorithms that generalize to accelerate the acquisition of entirely new, held-out tasks. We evaluate 6 state-of-the-art meta-reinforcement learning and multi-task learning algorithms on these tasks. Surprisingly, while each task and its variations (e.g., with different object positions) can be learned with reasonable success, these algorithms struggle to learn with multiple tasks at the same time, even with as few as ten distinct training tasks. Our analysis and open-source environments pave the way for future research in multi-task learning and meta-learning that can enable meaningful generalization, thereby unlocking the full potential of these methods.
Machine learning algorithms have found several applications in the field of robotics and control systems. The control systems community has started to show interest towards several machine learning algorithms from the sub-domains such as supervised learning, imitation learning and reinforcement learning to achieve autonomous control and intelligent decision making. Amongst many complex control problems, stable bipedal walking has been the most challenging problem. In this paper, we present an architecture to design and simulate a planar bipedal walking robot(BWR) using a realistic robotics simulator, Gazebo. The robot demonstrates successful walking behaviour by learning through several of its trial and errors, without any prior knowledge of itself or the world dynamics. The autonomous walking of the BWR is achieved using reinforcement learning algorithm called Deep Deterministic Policy Gradient(DDPG). DDPG is one of the algorithms for learning controls in continuous action spaces. After training the model in simulation, it was observed that, with a proper shaped reward function, the robot achieved faster walking or even rendered a running gait with an average speed of 0.83 m/s. The gait pattern of the bipedal walker was compared with the actual human walking pattern. The results show that the bipedal walking pattern had similar characteristics to that of a human walking pattern.
A recent research trend has emerged to identify developers' emotions, by applying sentiment analysis to the content of communication traces left in collaborative development environments. Trying to overcome the limitations posed by using off-the-shelf sentiment analysis tools, researchers recently started to develop their own tools for the software engineering domain. In this paper, we report a benchmark study to assess the performance and reliability of three sentiment analysis tools specifically customized for software engineering. Furthermore, we offer a reflection on the open challenges, as they emerge from a qualitative analysis of misclassified texts.
小貼士
登錄享
相關主題
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191