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.

This paper describes a computational model of multiagent multimodal categorization that realizes emergent communication. We clarify whether the computational model can reproduce the following functions in a symbol emergence system, comprising two agents with different sensory modalities playing a naming game. (1) Function for forming a shared lexical system that comprises perceptual categories and corresponding signs, formed by agents through individual learning and semiotic communication between agents. (2) Function to improve the categorization accuracy in an agent via semiotic communication with another agent, even when some sensory modalities of each agent are missing. (3) Function that an agent infers unobserved sensory information based on a sign sampled from another agent in the same manner as cross-modal inference. We propose an interpersonal multimodal Dirichlet mixture (Inter-MDM), which is derived by dividing an integrative probabilistic generative model, which is obtained by integrating two Dirichlet mixtures (DMs). The Markov chain Monte Carlo algorithm realizes emergent communication. The experimental results demonstrated that Inter-MDM enables agents to form multimodal categories and appropriately share signs between agents. It is shown that emergent communication improves categorization accuracy, even when some sensory modalities are missing. Inter-MDM enables an agent to predict unobserved information based on a shared sign.

Evaluating the general abilities of intelligent agents requires complex simulation environments. Existing benchmarks typically evaluate only one narrow task per environment, requiring researchers to perform expensive training runs on many different environments. We introduce Crafter, an open world survival game with visual inputs that evaluates a wide range of general abilities within a single environment. Agents either learn from the provided reward signal or through intrinsic objectives and are evaluated by semantically meaningful achievements that can be unlocked during each episode, such as discovering resources and crafting tools. Consistently unlocking all achievements requires strong generalization, deep exploration, and long-term reasoning. We experimentally verify that Crafter is of appropriate difficulty to drive future research and provide baselines scores of reward agents and unsupervised agents. Furthermore, we observe sophisticated behaviors emerging from maximizing the reward signal, such as building tunnel systems, bridges, houses, and plantations. We hope that Crafter will accelerate research progress by quickly evaluating a wide spectrum of abilities. Crafter is an open world survival game for reinforcement learning research. Shown in Figure 1, Crafter features randomly generated 2D worlds with forests, lakes, mountains, and caves. The player needs to forage for food and water, find shelter to sleep, defend against monsters, collect materials, and build tools.

We study the design of autonomous agents that are capable of deceiving outside observers about their intentions while carrying out tasks in stochastic, complex environments. By modeling the agent's behavior as a Markov decision process, we consider a setting where the agent aims to reach one of multiple potential goals while deceiving outside observers about its true goal. We propose a novel approach to model observer predictions based on the principle of maximum entropy and to efficiently generate deceptive strategies via linear programming. The proposed approach enables the agent to exhibit a variety of tunable deceptive behaviors while ensuring the satisfaction of probabilistic constraints on the behavior. We evaluate the performance of the proposed approach via comparative user studies and present a case study on the streets of Manhattan, New York, using real travel time distributions.

Reactive and safe agent modelings are important for nowadays traffic simulator designs and safe planning applications. In this work, we proposed a reactive agent model which can ensure safety without comprising the original purposes, by learning only high-level decisions from expert data and a low-level decentralized controller guided by the jointly learned decentralized barrier certificates. Empirical results show that our learned road user simulation models can achieve a significant improvement in safety comparing to state-of-the-art imitation learning and pure control-based methods, while being similar to human agents by having smaller errors to the expert data. Moreover, our learned reactive agents are shown to generalize better to unseen traffic conditions, and react better to other road users and therefore can help understand challenging planning problems pragmatically.

Multi-Agent reinforcement learning has received lot of attention in recent years and have applications in many different areas. Existing methods involving Centralized Training and Decentralized execution, attempts to train the agents towards learning a pattern of coordinated actions to arrive at optimal joint policy. However if some agents are stochastic to varying degrees of stochasticity, the above methods often fail to converge and provides poor coordination among agents. In this paper we show how this stochasticity of agents, which could be a result of malfunction or aging of robots, can add to the uncertainty in coordination and there contribute to unsatisfactory global coordination. In this case, the deterministic agents have to understand the behavior and limitations of the stochastic agents while arriving at optimal joint policy. Our solution, DSDF which tunes the discounted factor for the agents according to uncertainty and use the values to update the utility networks of individual agents. DSDF also helps in imparting an extent of reliability in coordination thereby granting stochastic agents tasks which are immediate and of shorter trajectory with deterministic ones taking the tasks which involve longer planning. Such an method enables joint co-ordinations of agents some of which may be partially performing and thereby can reduce or delay the investment of agent/robot replacement in many circumstances. Results on benchmark environment for different scenarios shows the efficacy of the proposed approach when compared with existing approaches.

Driving in a complex urban environment is a difficult task that requires a complex decision policy. In order to make informed decisions, one needs to gain an understanding of the long-range context and the importance of other vehicles. In this work, we propose to use Vision Transformer (ViT) to learn a driving policy in urban settings with birds-eye-view (BEV) input images. The ViT network learns the global context of the scene more effectively than with earlier proposed Convolutional Neural Networks (ConvNets). Furthermore, ViT's attention mechanism helps to learn an attention map for the scene which allows the ego car to determine which surrounding cars are important to its next decision. We demonstrate that a DQN agent with a ViT backbone outperforms baseline algorithms with ConvNet backbones pre-trained in various ways. In particular, the proposed method helps reinforcement learning algorithms to learn faster, with increased performance and less data than baselines.

An ideal integration of autonomous agents in a human world implies that they are able to collaborate on human terms. In particular, theory of mind plays an important role in maintaining common ground during human collaboration and communication. To enable theory of mind modeling in situated interactions, we introduce a fine-grained dataset of collaborative tasks performed by pairs of human subjects in the 3D virtual blocks world of Minecraft. It provides information that captures partners' beliefs of the world and of each other as an interaction unfolds, bringing abundant opportunities to study human collaborative behaviors in situated language communication. As a first step towards our goal of developing embodied AI agents able to infer belief states of collaborative partners in situ, we build and present results on computational models for several theory of mind tasks.

We consider a learning agent in a partially observable environment, with which the agent has never interacted before, and about which it learns both what it can observe and how its actions affect the environment. The agent can learn about this domain from experience gathered by taking actions in the domain and observing their results. We present learning algorithms capable of learning as much as possible (in a well-defined sense) both about what is directly observable and about what actions do in the domain, given the learner's observational constraints. We differentiate the level of domain knowledge attained by each algorithm, and characterize the type of observations required to reach it. The algorithms use dynamic epistemic logic (DEL) to represent the learned domain information symbolically. Our work continues that of Bolander and Gierasimczuk (2015), which developed DEL-based learning algorithms based to learn domain information in fully observable domains.

Driven by the need to capture users' evolving interests and optimize their long-term experiences, more and more recommender systems have started to model recommendation as a Markov decision process and employ reinforcement learning to address the problem. Shouldn't research on the fairness of recommender systems follow the same trend from static evaluation and one-shot intervention to dynamic monitoring and non-stop control? In this paper, we portray the recent developments in recommender systems first and then discuss how fairness could be baked into the reinforcement learning techniques for recommendation. Moreover, we argue that in order to make further progress in recommendation fairness, we may want to consider multi-agent (game-theoretic) optimization, multi-objective (Pareto) optimization, and simulation-based optimization, in the general framework of stochastic games.