Search

This paper proposes a generative probabilistic model integrating emergent communication and multi-agent reinforcement learning. The agents plan their actions by probabilistic inference, called control as inference, and communicate using messages that are latent variables and estimated based on the planned actions. Through these messages, each agent can send information about its actions and know information about the actions of another agent. Therefore, the agents change their actions according to the estimated messages to achieve cooperative tasks. This inference of messages can be considered as communication, and this procedure can be formulated by the Metropolis-Hasting naming game. Through experiments in the grid world environment, we show that the proposed PGM can infer meaningful messages to achieve the cooperative task.

In the studies on symbol emergence and emergent communication in a population of agents, a computational model was employed in which agents participate in various language games. Among these, the Metropolis-Hastings naming game (MHNG) possesses a notable mathematical property: symbol emergence through MHNG is proven to be a decentralized Bayesian inference of representations shared by the agents. However, the previously proposed MHNG is limited to a two-agent scenario. This paper extends MHNG to an N-agent scenario. The main contributions of this paper are twofold: (1) we propose the recursive Metropolis-Hastings naming game (RMHNG) as an N-agent version of MHNG and demonstrate that RMHNG is an approximate Bayesian inference method for the posterior distribution over a latent variable shared by agents, similar to MHNG; and (2) we empirically evaluate the performance of RMHNG on synthetic and real image data, enabling multiple agents to develop and share a symbol system. Furthermore, we introduce two types of approximations -- one-sample and limited-length -- to reduce computational complexity while maintaining the ability to explain communication in a population of agents. The experimental findings showcased the efficacy of RMHNG as a decentralized Bayesian inference for approximating the posterior distribution concerning latent variables, which are jointly shared among agents, akin to MHNG. Moreover, the utilization of RMHNG elucidated the agents' capacity to exchange symbols. Furthermore, the study discovered that even the computationally simplified version of RMHNG could enable symbols to emerge among the agents.

Creating autonomous robots that can actively explore the environment, acquire knowledge and learn skills continuously is the ultimate achievement envisioned in cognitive and developmental robotics. Their learning processes should be based on interactions with their physical and social world in the manner of human learning and cognitive development. Based on this context, in this paper, we focus on the two concepts of world models and predictive coding. Recently, world models have attracted renewed attention as a topic of considerable interest in artificial intelligence. Cognitive systems learn world models to better predict future sensory observations and optimize their policies, i.e., controllers. Alternatively, in neuroscience, predictive coding proposes that the brain continuously predicts its inputs and adapts to model its own dynamics and control behavior in its environment. Both ideas may be considered as underpinning the cognitive development of robots and humans capable of continual or lifelong learning. Although many studies have been conducted on predictive coding in cognitive robotics and neurorobotics, the relationship between world model-based approaches in AI and predictive coding in robotics has rarely been discussed. Therefore, in this paper, we clarify the definitions, relationships, and status of current research on these topics, as well as missing pieces of world models and predictive coding in conjunction with crucially related concepts such as the free-energy principle and active inference in the context of cognitive and developmental robotics. Furthermore, we outline the frontiers and challenges involved in world models and predictive coding toward the further integration of AI and robotics, as well as the creation of robots with real cognitive and developmental capabilities in the future., Comment: 28 pages, 3 figures

In this study, we propose a head-to-head type (H2H-type) inter-personal multimodal Dirichlet mixture (Inter-MDM) by modifying the original Inter-MDM, which is a probabilistic generative model that represents the symbol emergence between two agents as multiagent multimodal categorization. A Metropolis--Hastings method-based naming game based on the Inter-MDM enables two agents to collaboratively perform multimodal categorization and share signs with a solid mathematical foundation of convergence. However, the conventional Inter-MDM presumes a tail-to-tail connection across a latent word variable, causing inflexibility of the further extension of Inter-MDM for modeling a more complex symbol emergence. Therefore, we propose herein a head-to-head type (H2H-type) Inter-MDM that treats a latent word variable as a child node of an internal variable of each agent in the same way as many prior studies of multimodal categorization. On the basis of the H2H-type Inter-MDM, we propose a naming game in the same way as the conventional Inter-MDM. The experimental results show that the H2H-type Inter-MDM yields almost the same performance as the conventional Inter-MDM from the viewpoint of multimodal categorization and sign sharing., Comment: 7 pages, 4 figures, 5 tables

The present paper proposes a novel reinforcement learning method with world models, DreamingV2, a collaborative extension of DreamerV2 and Dreaming. DreamerV2 is a cutting-edge model-based reinforcement learning from pixels that uses discrete world models to represent latent states with categorical variables. Dreaming is also a form of reinforcement learning from pixels that attempts to avoid the autoencoding process in general world model training by involving a reconstruction-free contrastive learning objective. The proposed DreamingV2 is a novel approach of adopting both the discrete representation of DreamingV2 and the reconstruction-free objective of Dreaming. Compared to DreamerV2 and other recent model-based methods without reconstruction, DreamingV2 achieves the best scores on five simulated challenging 3D robot arm tasks. We believe that DreamingV2 will be a reliable solution for robot learning since its discrete representation is suitable to describe discontinuous environments, and the reconstruction-free fashion well manages complex vision observations., Comment: The code will be available soon

In the present paper, we propose a decoder-free extension of Dreamer, a leading model-based reinforcement learning (MBRL) method from pixels. Dreamer is a sample- and cost-efficient solution to robot learning, as it is used to train latent state-space models based on a variational autoencoder and to conduct policy optimization by latent trajectory imagination. However, this autoencoding based approach often causes object vanishing, in which the autoencoder fails to perceives key objects for solving control tasks, and thus significantly limiting Dreamer's potential. This work aims to relieve this Dreamer's bottleneck and enhance its performance by means of removing the decoder. For this purpose, we firstly derive a likelihood-free and InfoMax objective of contrastive learning from the evidence lower bound of Dreamer. Secondly, we incorporate two components, (i) independent linear dynamics and (ii) the random crop data augmentation, to the learning scheme so as to improve the training performance. In comparison to Dreamer and other recent model-free reinforcement learning methods, our newly devised Dreamer with InfoMax and without generative decoder (Dreaming) achieves the best scores on 5 difficult simulated robotics tasks, in which Dreamer suffers from object vanishing., Comment: Accepted to ICRA2021. Camera ready version

In the present paper, we propose an extension of the Deep Planning Network (PlaNet), also referred to as PlaNet of the Bayesians (PlaNet-Bayes). There has been a growing demand in model predictive control (MPC) in partially observable environments in which complete information is unavailable because of, for example, lack of expensive sensors. PlaNet is a promising solution to realize such latent MPC, as it is used to train state-space models via model-based reinforcement learning (MBRL) and to conduct planning in the latent space. However, recent state-of-the-art strategies mentioned in MBRR literature, such as involving uncertainty into training and planning, have not been considered, significantly suppressing the training performance. The proposed extension is to make PlaNet uncertainty-aware on the basis of Bayesian inference, in which both model and action uncertainty are incorporated. Uncertainty in latent models is represented using a neural network ensemble to approximately infer model posteriors. The ensemble of optimal action candidates is also employed to capture multimodal uncertainty in the optimality. The concept of the action ensemble relies on a general variational inference MPC (VI-MPC) framework and its instance, probabilistic action ensemble with trajectory sampling (PaETS). In this paper, we extend VI-MPC and PaETS, which have been originally introduced in previous literature, to address partially observable cases. We experimentally compare the performances on continuous control tasks, and conclude that our method can consistently improve the asymptotic performance compared with PlaNet.

State representation learning (SRL) in partially observable Markov decision processes has been studied to learn abstract features of data useful for robot control tasks. For SRL, acquiring domain-agnostic states is essential for achieving efficient imitation learning. Without these states, imitation learning is hampered by domain-dependent information useless for control. However, existing methods fail to remove such disturbances from the states when the data from experts and agents show large domain shifts. To overcome this issue, we propose a domain-adversarial and conditional state space model (DAC-SSM) that enables control systems to obtain domain-agnostic and task- and dynamics-aware states. DAC-SSM jointly optimizes the state inference, observation reconstruction, forward dynamics, and reward models. To remove domain-dependent information from the states, the model is trained with domain discriminators in an adversarial manner, and the reconstruction is conditioned on domain labels. We experimentally evaluated the model predictive control performance via imitation learning for continuous control of sparse reward tasks in simulators and compared it with the performance of the existing SRL method. The agents from DAC-SSM achieved performance comparable to experts and more than twice the baselines. We conclude domain-agnostic states are essential for imitation learning that has large domain shifts and can be obtained using DAC-SSM., Comment: Published at IROS 2020

This paper describes a framework for the development of an integrative cognitive system based on probabilistic generative models (PGMs) called Neuro-SERKET. Neuro-SERKET is an extension of SERKET, which can compose elemental PGMs developed in a distributed manner and provide a scheme that allows the composed PGMs to learn throughout the system in an unsupervised way. In addition to the head-to-tail connection supported by SERKET, Neuro-SERKET supports tail-to-tail and head-to-head connections, as well as neural network-based modules, i.e., deep generative models. As an example of a Neuro-SERKET application, an integrative model was developed by composing a variational autoencoder (VAE), a Gaussian mixture model (GMM), latent Dirichlet allocation (LDA), and automatic speech recognition (ASR). The model is called VAE+GMM+LDA+ASR. The performance of VAE+GMM+LDA+ASR and the validity of Neuro-SERKET were demonstrated through a multimodal categorization task using image data and a speech signal of numerical digits., Comment: New Gener. Comput. (2020)

It is an effective strategy for the multi-person pose tracking task in videos to employ prediction and pose matching in a frame-by-frame manner. For this type of approach, uncertainty-aware modeling is essential because precise prediction is impossible. However, previous studies have relied on only a single prediction without incorporating uncertainty, which can cause critical tracking errors if the prediction is unreliable. This paper proposes an extension to this approach with Sequential Monte Carlo (SMC). This naturally reformulates the tracking scheme to handle multiple predictions (or hypotheses) of poses, thereby mitigating the negative effect of prediction errors. An important component of SMC, i.e., a proposal distribution, is designed as a probabilistic neural pose predictor, which can propose diverse and plausible hypotheses by incorporating epistemic uncertainty and heteroscedastic aleatoric uncertainty. In addition, a recurrent architecture is introduced to our neural modeling to utilize time-sequence information of poses to manage difficult situations, such as the frequent disappearance and reappearances of poses. Compared to existing baselines, the proposed method achieves a state-of-the-art MOTA score on the PoseTrack2018 validation dataset by reducing approximately 50% of tracking errors from a state-of-the art baseline method., Comment: Accepted to ICRA2020; Camera-ready ver

In recent studies on model-based reinforcement learning (MBRL), incorporating uncertainty in forward dynamics is a state-of-the-art strategy to enhance learning performance, making MBRLs competitive to cutting-edge model free methods, especially in simulated robotics tasks. Probabilistic ensembles with trajectory sampling (PETS) is a leading type of MBRL, which employs Bayesian inference to dynamics modeling and model predictive control (MPC) with stochastic optimization via the cross entropy method (CEM). In this paper, we propose a novel extension to the uncertainty-aware MBRL. Our main contributions are twofold: Firstly, we introduce a variational inference MPC, which reformulates various stochastic methods, including CEM, in a Bayesian fashion. Secondly, we propose a novel instance of the framework, called probabilistic action ensembles with trajectory sampling (PaETS). As a result, our Bayesian MBRL can involve multimodal uncertainties both in dynamics and optimal trajectories. In comparison to PETS, our method consistently improves asymptotic performance on several challenging locomotion tasks., Comment: Accepted to CoRL2019. Camera-ready ver

Integration of reinforcement learning and imitation learning is an important problem that has been studied for a long time in the field of intelligent robotics. Reinforcement learning optimizes policies to maximize the cumulative reward, whereas imitation learning attempts to extract general knowledge about the trajectories demonstrated by experts, i.e., demonstrators. Because each of them has their own drawbacks, methods combining them and compensating for each set of drawbacks have been explored thus far. However, many of the methods are heuristic and do not have a solid theoretical basis. In this paper, we present a new theory for integrating reinforcement and imitation learning by extending the probabilistic generative model framework for reinforcement learning, {\it plan by inference}. We develop a new probabilistic graphical model for reinforcement learning with multiple types of rewards and a probabilistic graphical model for Markov decision processes with multiple optimality emissions (pMDP-MO). Furthermore, we demonstrate that the integrated learning method of reinforcement learning and imitation learning can be formulated as a probabilistic inference of policies on pMDP-MO by considering the output of the discriminator in generative adversarial imitation learning as an additional optimal emission observation. We adapt the generative adversarial imitation learning and task-achievement reward to our proposed framework, achieving significantly better performance than agents trained with reinforcement learning or imitation learning alone. Experiments demonstrate that our framework successfully integrates imitation and reinforcement learning even when the number of demonstrators is only a few., Comment: Submitted to Advanced Robotics

We propose a novel online learning algorithm, called SpCoSLAM 2.0, for spatial concepts and lexical acquisition with high accuracy and scalability. Previously, we proposed SpCoSLAM as an online learning algorithm based on unsupervised Bayesian probabilistic model that integrates multimodal place categorization, lexical acquisition, and SLAM. However, our original algorithm had limited estimation accuracy owing to the influence of the early stages of learning, and increased computational complexity with added training data. Therefore, we introduce techniques such as fixed-lag rejuvenation to reduce the calculation time while maintaining an accuracy higher than that of the original algorithm. The results show that, in terms of estimation accuracy, the proposed algorithm exceeds the original algorithm and is comparable to batch learning. In addition, the calculation time of the proposed algorithm does not depend on the amount of training data and becomes constant for each step of the scalable algorithm. Our approach will contribute to the realization of long-term spatial language interactions between humans and robots., Comment: Accepted to Autonomous Robots (24 January 2020)

Human infants can discover words directly from unsegmented speech signals without any explicitly labeled data. In this paper, we develop a novel machine learning method called nonparametric Bayesian double articulation analyzer (NPB-DAA) that can directly acquire language and acoustic models from observed continuous speech signals. For this purpose, we propose an integrative generative model that combines a language model and an acoustic model into a single generative model called the "hierarchical Dirichlet process hidden language model" (HDP-HLM). The HDP-HLM is obtained by extending the hierarchical Dirichlet process hidden semi-Markov model (HDP-HSMM) proposed by Johnson et al. An inference procedure for the HDP-HLM is derived using the blocked Gibbs sampler originally proposed for the HDP-HSMM. This procedure enables the simultaneous and direct inference of language and acoustic models from continuous speech signals. Based on the HDP-HLM and its inference procedure, we developed a novel double articulation analyzer. By assuming HDP-HLM as a generative model of observed time series data, and by inferring latent variables of the model, the method can analyze latent double articulation structure, i.e., hierarchically organized latent words and phonemes, of the data in an unsupervised manner. The novel unsupervised double articulation analyzer is called NPB-DAA. The NPB-DAA can automatically estimate double articulation structure embedded in speech signals. We also carried out two evaluation experiments using synthetic data and actual human continuous speech signals representing Japanese vowel sequences. In the word acquisition and phoneme categorization tasks, the NPB-DAA outperformed a conventional double articulation analyzer (DAA) and baseline automatic speech recognition system whose acoustic model was trained in a supervised manner., Comment: 15 pages, 7 figures, Draft submitted to IEEE Transactions on Autonomous Mental Development (TAMD)