Collaborating Authors


Using deep learning to control the unconsciousness level of patients in an anesthetic state


In recent years, researchers have been developing machine learning algorithms for an increasingly wide range of purposes. This includes algorithms that can be applied in healthcare settings, for instance helping clinicians to diagnose specific diseases or neuropsychiatric disorders or monitor the health of patients over time. Researchers at Massachusetts Institute of Technology (MIT) and Massachusetts General Hospital have recently carried out a study investigating the possibility of using deep reinforcement learning to control the levels of unconsciousness of patients who require anesthesia for a medical procedure. Their paper, set to be published in the proceedings of the 2020 International Conference on Artificial Intelligence in Medicine, was voted the best paper presented at the conference. "Our lab has made significant progress in understanding how anesthetic medications affect neural activity and now has a multidisciplinary team studying how to accurately determine anesthetic doses from neural recordings," Gabriel Schamberg, one of the researchers who carried out the study, told TechXplore.

Reinforcement Learning Approaches in Social Robotics Artificial Intelligence

In order to facilitate natural interaction, researchers in social robotics have focused on robots that can adapt to diverse conditions and to the different users with whom they interact. Recently, there has been great interest in the use of machine learning methods for adaptive social robots [48], [29], [106], [45], [49], [86]. Machine Learning (ML) algorithms can be categorized into three subfields [2]: supervised learning, unsupervised learning and reinforcement learning. In supervised learning, correct input/output pairs are available and the goal is to find a correct mapping from input to output space. In unsupervised learning, output data is not available and the goal is to find patterns in the input data. Reinforcement Learning (RL) [96] is a framework for decision-making problems in which an agent interacts through trial-and-error with its environment to discover an optimal behavior. The agent does not receive direct feedback of correctness, instead it receives scarce feedback about the actions it has taken in the past.

Parameter-based Value Functions Artificial Intelligence

Learning value functions off-policy is at the core of modern Reinforcement Learning (RL). Traditional off-policy actor-critic algorithms, however, only approximate the true policy gradient, since the gradient $\nabla_{\theta} Q^{\pi_{\theta}}(s,a)$ of the action-value function with respect to the policy parameters is often ignored. We introduce a class of value functions called Parameter-based Value Functions (PVFs) whose inputs include the policy parameters. PVFs can evaluate the performance of any policy given a state, a state-action pair, or a distribution over the RL agent's initial states. We show how PVFs yield exact policy gradient theorems. We derive off-policy actor-critic algorithms based on PVFs trained using Monte Carlo or Temporal Difference methods. Preliminary experimental results indicate that PVFs can effectively evaluate deterministic linear and nonlinear policies, outperforming state-of-the-art algorithms in the continuous control environment Swimmer-v3. Finally, we show how recurrent neural networks can be trained through PVFs to solve supervised and RL problems involving partial observability and long time lags between relevant events. This provides an alternative to backpropagation through time.

Learning Reusable Options for Multi-Task Reinforcement Learning Artificial Intelligence

One of the main reasons why RL has worked so well in these applications is that we are able simulate millions of interactions with the environment in a relatively short period of time, allowing the agent to experience a large number of different situations in the environment and learn the consequences of its actions. In many real world applications, however, where the agent interacts with the physical world, it might not be easy to generate such a large number of interactions. The time and cost associated with training such systems could render RL an unfeasible approach for training in large scale. As a concrete example, consider training a large number of humanoid robots (agents) to move quickly, as in the Robocup competition [ Farchy et al., 2013 ] . Although the agents have similar dynamics, subtle variations mean that a single policy shared across all agents would not be an effective solution.

Let's Play Again: Variability of Deep Reinforcement Learning Agents in Atari Environments Artificial Intelligence

Reproducibility in reinforcement learning is challenging: uncontrolled stochasticity from many sources, such as the learning algorithm, the learned policy, and the environment itself have led researchers to report the performance of learned agents using aggregate metrics of performance over multiple random seeds for a single environment. Unfortunately, there are still pernicious sources of variability in reinforcement learning agents that make reporting common summary statistics an unsound metric for performance. Our experiments demonstrate the variability of common agents used in the popular OpenAI Baselines repository. We make the case for reporting post-training agent performance as a distribution, rather than a point estimate.

Reinforcement Learning: Connections, Surprises, and Challenge

AI Magazine

The idea of implementing reinforcement learning in a computer was one of the earliest ideas about the possibility of AI, but reinforcement learning remained on the margin of AI until relatively recently. Today we see reinforcement learning playing essential roles in some of the most impressive AI applications. This article presents observations from the author’s personal experience with reinforcement learning over the most recent 40 years of its history in AI, focusing on striking connections that emerged between largely separate disciplines and on some of the findings that surprised him along the way. These connections and surprises place reinforcement learning in a historical context, and they help explain the success it is finding in modern AI. The article concludes by discussing some of the challenges that need to be faced as reinforcement learning moves out into real world.

Improved robustness of reinforcement learning policies upon conversion to spiking neuronal network platforms applied to ATARI games Machine Learning

Various implementations of Deep Reinforcement Learning (RL) demonstrated excellent performance on tasks that can be solved by trained policy, but they are not without drawbacks. Deep RL suffers from high sensitivity to noisy and missing input and adversarial attacks. To mitigate these deficiencies of deep RL solutions, we suggest involving spiking neural networks (SNNs). Previous work has shown that standard Neural Networks trained using supervised learning for image classification can be converted to SNNs with negligible deterioration in performance. In this paper, we convert Q-Learning ReLU-Networks (ReLU-N) trained using reinforcement learning into SNN. We provide a proof of concept for the conversion of ReLU-N to SNN demonstrating improved robustness to occlusion and better generalization than the original ReLU-N. Moreover, we show promising initial results with converting full-scale Deep Q-networks to SNNs, paving the way for future research.

A Compression-Inspired Framework for Macro Discovery Artificial Intelligence

In this paper we consider the problem of how a reinforcement learning agent tasked with solving a set of related Markov decision processes can use knowledge acquired early in its lifetime to improve its ability to more rapidly solve novel, but related, tasks. One way of exploiting this experience is by identifying recurrent patterns in trajectories obtained from well-performing policies. We propose a three-step framework in which an agent 1) generates a set of candidate open-loop macros by compressing trajectories drawn from near-optimal policies; 2) evaluates the value of each macro; and 3) selects a maximally diverse subset of macros that spans the space of policies typically required for solving the set of related tasks. Our experiments show that extending the original primitive action-set of the agent with the identified macros allows it to more rapidly learn an optimal policy in unseen, but similar MDPs.

Robbins-Mobro conditions for persistent exploration learning strategies Machine Learning

We formulate simple assumptions, implying the Robbins-Monro conditions for the $Q$-learning algorithm with the local learning rate, depending on the number of visits of a particular state-action pair (local clock) and the number of iteration (global clock). It is assumed that the Markov decision process is communicating and the learning policy ensures the persistent exploration. The restrictions are imposed on the functional dependence of the learning rate on the local and global clocks. The result partially confirms the conjecture of Bradkte (1994).

Symbol Emergence in Cognitive Developmental Systems: a Survey Artificial Intelligence

Humans use signs, e.g., sentences in a spoken language, for communication and thought. Hence, symbol systems like language are crucial for our communication with other agents and adaptation to our real-world environment. The symbol systems we use in our human society adaptively and dynamically change over time. In the context of artificial intelligence (AI) and cognitive systems, the symbol grounding problem has been regarded as one of the central problems related to {\it symbols}. However, the symbol grounding problem was originally posed to connect symbolic AI and sensorimotor information and did not consider many interdisciplinary phenomena in human communication and dynamic symbol systems in our society, which semiotics considered. In this paper, we focus on the symbol emergence problem, addressing not only cognitive dynamics but also the dynamics of symbol systems in society, rather than the symbol grounding problem. We first introduce the notion of a symbol in semiotics from the humanities, to leave the very narrow idea of symbols in symbolic AI. Furthermore, over the years, it became more and more clear that symbol emergence has to be regarded as a multifaceted problem. Therefore, secondly, we review the history of the symbol emergence problem in different fields, including both biological and artificial systems, showing their mutual relations. We summarize the discussion and provide an integrative viewpoint and comprehensive overview of symbol emergence in cognitive systems. Additionally, we describe the challenges facing the creation of cognitive systems that can be part of symbol emergence systems.