We propose a fully decentralized multi-agent world model that enables both symbol emergence for communication and coordinated behavior through temporal extension of collective predictive coding. Unlike previous research that focuses on either communication or coordination separately, our approach achieves both simultaneously. Our method integrates world models with communication channels, enabling agents to predict environmental dynamics, estimate states from partial observations, and share critical information through bidirectional message exchange with contrastive learning for message alignment. Using a two-agent trajectory drawing task, we demonstrate that our communication-based approach outperforms non-communicative models when agents have divergent perceptual capabilities, achieving the second-best coordination after centralized models. Importantly, our decentralized approach with constraints preventing direct access to other agents' internal states facilitates the emergence of more meaningful symbol systems that accurately reflect environmental states. These findings demonstrate the effectiveness of decentralized communication for supporting coordination while developing shared representations of the environment.

Evolutionary robot systems are usually affected by the properties of the environment indirectly through selection. In this paper, we present and investigate a system where the environment also has a direct effect: through regulation. We propose a novel robot encoding method where a genotype encodes multiple possible phenotypes, and the incarnation of a robot depends on the environmental conditions taking place in a determined moment of its life. This means that the morphology, controller, and behavior of a robot can change according to the environment. Importantly, this process of development can happen at any moment of a robot lifetime, according to its experienced environmental stimuli. We provide an empirical proof-of-concept, and the analysis of the experimental results shows that Plasticoding improves adaptation (task performance) while leading to different evolved morphologies, controllers, and behaviour.

To survive in dynamic and uncertain environments, individuals must develop effective decision strategies that balance information gathering and decision commitment. Models of such strategies often prioritize either optimizing tangible payoffs, like reward rate, or gathering information to support a diversity of (possibly unknown) objectives. However, our understanding of the relative merits of these two approaches remains incomplete, in part because direct comparisons have been limited to idealized, static environments that lack the dynamic complexity of the real world. Here we compared the performance of normative reward- and information-seeking strategies in a dynamic foraging task. Both strategies show similar transitions between exploratory and exploitative behaviors as environmental uncertainty changes. However, we find subtle disparities in the actions they take, resulting in meaningful performance differences: whereas reward-seeking strategies generate slightly more reward on average, information-seeking strategies provide more consistent and predictable outcomes. Our findings support the adaptive value of information-seeking behaviors that can mitigate risk with minimal reward loss.

Reinforcement learning in non-stationary environments is challenging due to abrupt and unpredictable changes in dynamics, often causing traditional algorithms to fail to converge. However, in many real-world cases, non-stationarity has some structure that can be exploited to develop algorithms and facilitate theoretical analysis. We introduce one such structure, Switching Non-Stationary Markov Decision Processes (SNS-MDP), where environments switch over time-based on an underlying Markov chain. Under a fixed policy, the value function of an SNS-MDP admits a closed-form solution determined by the Markov chain's statistical properties, and despite the inherent non-stationarity, Temporal Difference (TD) learning methods still converge to the correct value function. Furthermore, policy improvement can be performed, and it is shown that policy iteration converges to the optimal policy. Moreover, since Q-learning converges to the optimal Q-function, it likewise yields the corresponding optimal policy. To illustrate the practical advantages of SNS-MDPs, we present an example in communication networks where channel noise follows a Markovian pattern, demonstrating how this framework can effectively guide decision-making in complex, time-varying contexts.

Adaptive sampling and planning in robotic environmental monitoring are challenging when the target environmental process varies over space and time. The underlying environmental dynamics require the planning module to integrate future environmental changes so that action decisions made earlier do not quickly become outdated. We propose a Monte Carlo tree search method which not only well balances the environment exploration and exploitation in space, but also catches up to the temporal environmental dynamics. This is achieved by incorporating multi-objective optimization and a look-ahead model-predictive rewarding mechanism. We show that by allowing the robot to leverage the simulated and predicted spatiotemporal environmental process, the proposed informative planning approach achieves a superior performance after comparing with other baseline methods in terms of the root mean square error of the environment model and the distance to the ground truth.

We are about to see a significant change in the role of simulation to evaluate real-time what-if scenarios in materializing machine intelligence. I believe that it can play an even more purposeful role if expanded to include agent-based simulation at inference time. This type of computation seeks to iteratively resolve problems based on inputs from multiple agents (humans or other AIs) which is characteristic of more real-world learning. As such, it has the potential to impart multiple "models of mind" during the machine learning process and advance the next generation of AI. To ground the discussion below, we need to start with a definition of simulation in the context of this discussion.

In this work we derive and present evolutionary reinforcement learning dynamics in which the agents are irreducibly uncertain about the current state of the environment. We evaluate the dynamics across different classes of partially observable agent-environment systems and find that irreducible environmental uncertainty can lead to better learning outcomes faster, stabilize the learning process and overcome social dilemmas. However, as expected, we do also find that partial observability may cause worse learning outcomes, for example, in the form of a catastrophic limit cycle. Compared to fully observant agents, learning with irreducible environmental uncertainty often requires more exploration and less weight on future rewards to obtain the best learning outcomes. Furthermore, we find a range of dynamical effects induced by partial observability, e.g., a critical slowing down of the learning processes between reward regimes and the separation of the learning dynamics into fast and slow directions. The presented dynamics are a practical tool for researchers in biology, social science and machine learning to systematically investigate the evolutionary effects of environmental uncertainty.

Following decades of sustained improvement, metaheuristics are one of the great success stories of optimization research. However, in order for research in metaheuristics to avoid fragmentation and a lack of reproducibility, there is a pressing need for stronger scientific and computational infrastructure to support the development, analysis and comparison of new approaches. We argue that, via principled choice of infrastructure support, the field can pursue a higher level of scientific enquiry. We describe our vision and report on progress, showing how the adoption of common protocols for all metaheuristics can help liberate the potential of the field, easing the exploration of the design space of metaheuristics.

Human learning and intelligence work differently from the supervised pattern recognition approach adopted in most deep learning architectures. Humans seem to learn rich representations by exploration and imitation, build causal models of the world, and use both to flexibly solve new tasks. We suggest a simple but effective unsupervised model which develops such characteristics. The agent learns to represent the dynamical physical properties of its environment by intrinsically motivated exploration, and performs inference on this representation to reach goals. For this, a set of self-organizing maps which represent state-action pairs is combined with a causal model for sequence prediction. The proposed system is evaluated in the cartpole environment. After an initial phase of playful exploration, the agent can execute kinematic simulations of the environment's future, and use those for action planning. We demonstrate its performance on a set of several related, but different one-shot imitation tasks, which the agent flexibly solves in an active inference style.

Continuous reinforcement learning such as DDPG and A3C are widely used in robot control and autonomous driving. However, both methods have theoretical weaknesses. While DDPG cannot control noises in the control process, A3C does not satisfy the continuity conditions under the Gaussian policy. To address these concerns, we propose a new continues reinforcement learning method based on stochastic differential equations and we call it Incremental Reinforcement Learning (IRL). This method not only guarantees the continuity of actions within any time interval, but controls the variance of actions in the training process. In addition, our method does not assume Markov control in agents' action control and allows agents to predict scene changes for action selection. With our method, agents no longer passively adapt to the environment. Instead, they positively interact with the environment for maximum rewards.