Category Archives: Cognitive Sciences

A novel RL setting for non-Markovian systems

April 26, 2024 09:38 ,

Ronen I. Brafman, Giuseppe De Giacomo, Regular decision processes, Artificial Intelligence, Volume 331, 2024 DOI: 10.1016/j.artint.2024.104113.

We introduce and study Regular Decision Processes (RDPs), a new, compact model for domains with non-Markovian dynamics and rewards, in which the dependence on the past is regular, in the language theoretic sense. RDPs are an intermediate model between MDPs and POMDPs. They generalize k-order MDPs and can be viewed as a POMDP in which the hidden state is a regular function of the entire history. In factored RDPs, transition and reward functions are specified using formulas in linear temporal logics over finite traces, or using regular expressions. This allows specifying complex dependence on the past using intuitive and compact formulas, and building models of partially observable domains without specifying an underlying state space.

Posted in: Reinforcement learning in AI , Tagged: , ,

The problem of incorporating novelties into the knowledge of an AI agent

April 26, 2024 09:34 ,

Shivam Goel, Panagiotis Lymperopoulos, Ravenna Thielstrom, Evan Krause, Patrick Feeney, Pierrick Lorang, Sarah Schneider, Yichen Wei, Eric Kildebeck, Stephen Goss, Michael C. Hughes, Liping Liu, Jivko Sinapov, Matthias Scheutz, A neurosymbolic cognitive architecture framework for handling novelties in open worlds, Artificial Intelligence, Volume 331, 2024 DOI: 10.1016/j.artint.2024.104111.

“Open world” environments are those in which novel objects, agents, events, and more can appear and contradict previous understandings of the environment. This runs counter to the “closed world” assumption used in most AI research, where the environment is assumed to be fully understood and unchanging. The types of environments AI agents can be deployed in are limited by the inability to handle the novelties that occur in open world environments. This paper presents a novel cognitive architecture framework to handle open-world novelties. This framework combines symbolic planning, counterfactual reasoning, reinforcement learning, and deep computer vision to detect and accommodate novelties. We introduce general algorithms for exploring open worlds using inference and machine learning methodologies to facilitate novelty accommodation. The ability to detect and accommodate novelties allows agents built on this framework to successfully complete tasks despite a variety of novel changes to the world. Both the framework components and the entire system are evaluated in Minecraft-like simulated environments. Our results indicate that agents are able to efficiently complete tasks while accommodating “concealed novelties” not shared with the architecture development team.

Posted in: Artificial Intelligence , Tagged:

Imitating physiological processes for achieving robot-human social interaction

April 26, 2024 09:31 ,

Marcos Maroto-Gómez, Martín Bueno-Adrada, María Malfaz, Álvaro Castro-González, Miguel Ángel Salichs, Human–robot pair-bonding from a neuroendocrine perspective: Modeling the effect of oxytocin, arginine vasopressin, and dopamine on the social behavior of an autonomous robot, Robotics and Autonomous Systems, Volume 176, 2024 DOI: 10.1016/j.robot.2024.104687.

Robots and humans coexist in various social environments. In these contexts, robots predominantly serve as assistants, necessitating communication and understanding capabilities. This paper introduces a biologically inspired model grounded on neuroendocrine substances that facilitate the development of social bonds between robots and individuals. The model simulates the effects of oxytocin, arginine vasopressin, and dopamine on social behavior, acting as modulators for bonding in the interaction between the social robot Mini and its users. Neuroendocrine levels vary in response to circadian rhythms and social stimuli perceived by the robot. If users express care for the robot, a positive bond is established, enhancing human–robot interaction by prompting the robot to engage in cooperative actions such as playing or communicating more frequently. Conversely, mistreating the robot leads to a deterioration of the relationship, causing user rejection. An experimenter-robot interaction scenario illustrates the model’s adaptive mechanisms involving three types of profiles: Friendly, Aversive, and Naive. Besides, a user study with 22 participants was conducted to analyze the differences in Attachment, Social Presence, perceived Anthropomorphism, Likability, and User Experience between a robot randomly selecting its behavior and a robot behaving using the bioinspired pair-bonded method proposed in this contribution. The results show how the pair-bonding with the user regulates the robot’s social behavior in response to user actions. The user study reveals statistical differences favoring the robot using the pair-bonding regulation in Attachment and Social Presence. A qualitative study using an interview-like form suggests the positive effects of creating bonds with bioinspired robots.

Posted in: Psycho-physiological bases of engineering , Tagged:

What attention is (from a cognitive science point of view)

April 3, 2024 13:06 ,

Wayne Wu, We know what attention is!, Trends in Cognitive Sciences, Volume 28, Issue 4, 2024 DOI: 10.1016/j.tics.2023.11.007.

Attention is one of the most thoroughly investigated psychological phenomena, yet skepticism about attention is widespread: we do not know what it is, it is too many things, there is no such thing. The deficiencies highlighted are not about experimental work but the adequacy of the scientific theory of attention. Combining common scientific claims about attention into a single theory leads to internal inconsistency. This paper demonstrates that a specific functional conception of attention is incorporated into the tasks used in standard experimental paradigms. In accepting these paradigms as valid probes of attention, we commit to this common conception. The conception unifies work at multiple levels of analysis into a coherent scientific explanation of attention. Thus, we all know what attention is.

Posted in: Psycho-physiological bases of engineering , Tagged:

On how much imagery can be said to be real or not by the human brain

April 3, 2024 13:03 ,

Rebecca Keogh, Reality check: how do we know what’s real?, Trends in Cognitive Sciences, Volume 28, Issue 4, 2024 DOI: 10.1016/j.tics.2023.06.001.

How do we know what is real and what is merely a figment of our imagination? Dijkstra and Fleming tackle this question in a recent study. In contrast to the classic Perky effect, they found that once imagery crosses a ‘reality threshold’, it becomes difficult to distinguish from reality.

Posted in: Psycho-physiological bases of engineering , Tagged:

POMDPs focused on obtaining policies that can be understood well just through the observation of the robot actions

April 3, 2024 12:39 ,

Miguel Faria, Francisco S. Melo, Ana Paiva, “Guess what I’m doing”: Extending legibility to sequential decision tasks, Artificial Intelligence, Volume 330, 2024 DOI: 10.1016/j.artint.2024.104107.

In this paper we investigate the notion of legibility in sequential decision tasks under uncertainty. Previous works that extend legibility to scenarios beyond robot motion either focus on deterministic settings or are computationally too expensive. Our proposed approach, dubbed PoLMDP, is able to handle uncertainty while remaining computationally tractable. We establish the advantages of our approach against state-of-the-art approaches in several scenarios of varying complexity. We also showcase the use of our legible policies as demonstrations in machine teaching scenarios, establishing their superiority in teaching new behaviours against the commonly used demonstrations based on the optimal policy. Finally, we assess the legibility of our computed policies through a user study, where people are asked to infer the goal of a mobile robot following a legible policy by observing its actions.

Posted in: Reinforcement learning in AI , Tagged: , ,

On the influence of the representations obtained through Deep RL in the learning process

April 3, 2024 12:35 ,

Han Wang, Erfan Miahi, Martha White, Marlos C. Machado, Zaheer Abbas, Raksha Kumaraswamy, Vincent Liu, Adam White, Investigating the properties of neural network representations in reinforcement learning, Artificial Intelligence, Volume 330, 2024 DOI: 10.1016/j.artint.2024.104100.

In this paper we investigate the properties of representations learned by deep reinforcement learning systems. Much of the early work on representations for reinforcement learning focused on designing fixed-basis architectures to achieve properties thought to be desirable, such as orthogonality and sparsity. In contrast, the idea behind deep reinforcement learning methods is that the agent designer should not encode representational properties, but rather that the data stream should determine the properties of the representation—good representations emerge under appropriate training schemes. In this paper we bring these two perspectives together, empirically investigating the properties of representations that support transfer in reinforcement learning. We introduce and measure six representational properties over more than 25,000 agent-task settings. We consider Deep Q-learning agents with different auxiliary losses in a pixel-based navigation environment, with source and transfer tasks corresponding to different goal locations. We develop a method to better understand why some representations work better for transfer, through a systematic approach varying task similarity and measuring and correlating representation properties with transfer performance. We demonstrate the generality of the methodology by investigating representations learned by a Rainbow agent that successfully transfers across Atari 2600 game modes.

Posted in: Reinforcement learning in AI , Tagged:

Using RL as a framework to study political issues

March 7, 2024 09:33 ,

Lion Schulz, Rahul Bhui, Political reinforcement learners, Trends in Cognitive Sciences, Volume 28, Issue 3, 2024, Pages 210-222 DOI: 10.1016/j.tics.2023.12.001.

Politics can seem home to the most calculating and yet least rational elements of humanity. How might we systematically characterize this spectrum of political cognition? Here, we propose reinforcement learning (RL) as a unified framework to dissect the political mind. RL describes how agents algorithmically navigate complex and uncertain domains like politics. Through this computational lens, we outline three routes to political differences, stemming from variability in agents\u2019 conceptions of a problem, the cognitive operations applied to solve the problem, or the backdrop of information available from the environment. A computational vantage on maladies of the political mind offers enhanced precision in assessing their causes, consequences, and cures.

Posted in: Cognitive sciences , Tagged: ,

Object oriented paradigm to improve transfer learning in RL, i.e., a sort of symbolic abstraction mechanism

March 1, 2024 10:05 ,

Ofir Marom, Benjamin Rosman, Transferable dynamics models for efficient object-oriented reinforcement learning, Robotics and Autonomous Systems, Volume 174, 2024 DOI: 10.1016/j.artint.2024.104079.

The Reinforcement Learning (RL) framework offers a general paradigm for constructing autonomous agents that can make effective decisions when solving tasks. An important area of study within the field of RL is transfer learning, where an agent utilizes knowledge gained from solving previous tasks to solve a new task more efficiently. While the notion of transfer learning is conceptually appealing, in practice, not all RL representations are amenable to transfer learning. Moreover, much of the research on transfer learning in RL is purely empirical. Previous research has shown that object-oriented representations are suitable for the purposes of transfer learning with theoretical efficiency guarantees. Such representations leverage the notion of object classes to learn lifted rules that apply to grounded object instantiations. In this paper, we extend previous research on object-oriented representations and introduce two formalisms: the first is based on deictic predicates, and is used to learn a transferable transition dynamics model; the second is based on propositions, and is used to learn a transferable reward dynamics model. In addition, we extend previously introduced efficient learning algorithms for object-oriented representations to our proposed formalisms. Our frameworks are then combined into a single efficient algorithm that learns transferable transition and reward dynamics models across a domain of related tasks. We illustrate our proposed algorithm empirically on an extended version of the Taxi domain, as well as the more difficult Sokoban domain, showing the benefits of our approach with regards to efficient learning and transfer.

Posted in: Reinforcement learning in AI , Tagged: ,

Improving sample efficiency of RL through memory reconstruction

February 15, 2024 09:29 ,

Y. Kang et al., Sample Efficient Reinforcement Learning Using Graph-Based Memory Reconstruction, IEEE Transactions on Artificial Intelligence, vol. 5, no. 2, pp. 751-762, Feb. 2024 DOI: 10.1109/TAI.2023.3268612.

Reinforcement learning (RL) algorithms typically require orders of magnitude more interactions than humans to learn effective policies. Research on memory in neuroscience suggests that humans’ learning efficiency benefits from associating their experiences and reconstructing potential events. Inspired by this finding, we introduce a human brainlike memory structure for agents and build a general learning framework based on this structure to improve the RL sampling efficiency. Since this framework is similar to the memory reconstruction process in psychology, we name the newly proposed RL framework as graph-based memory reconstruction (GBMR). In particular, GBMR first maintains an attribute graph on the agent’s memory and then retrieves its critical nodes to build and update potential paths among these nodes. This novel pipeline drives the RL agent to learn faster with its memory-enhanced value functions and reduces interactions with the environment by reconstructing its valuable paths. Extensive experimental analyses and evaluations in the grid maze and some challenging Atari environments demonstrate GBMRs superiority over traditional RL methods. We will release the source code and trained models to facilitate further studies in this research direction.

Posted in: Reinforcement learning in AI , Tagged: