We introduce a novel virtual robotic toolkit myGym, developed for reinforcement learning (RL), intrinsic motivation and imitation learning tasks trained in a 3D simulator. The trained tasks can then be easily transferred to real-world robotic scenarios. The modular structure of the simulator enables users to train and validate their algorithms on a large number of scenarios with various robots, environments and tasks. Compared to existing toolkits (e.g. OpenAI Gym, Roboschool) which are suitable for classical RL, myGym is also prepared for visuomotor (combining vision & movement) unsupervised tasks that require intrinsic motivation, i.e. the robots are able to generate their own goals. There are also collaborative scenarios intended for human-robot interaction. The toolkit provides pretrained visual modules for visuomotor tasks allowing rapid prototyping, and, moreover, users can customize the visual submodules and retrain with their own set of objects. In practice, the user selects the desired environment, robot, objects, task and type of reward as simulation parameters, and the training, visualization and testing themselves are handled automatically. The user can thus fully focus on development of the neural network architecture while controlling the behaviour of the environment using predefined parameters.

Reward Human Similarity solve challenging tasks in unknown environments. Objective Correlation Correlation However, manually crafting reward functions can be time consuming, expensive, and error prone to Task Reward 1.00 0.67 human error. Competing objectives have been Human Similarity 0.67 1.00 proposed for agents to learn without external Input Entropy 0.54 0.89 supervision, but it has been unclear how well they reflect task rewards or human behavior. To Information Gain 0.49 0.79 accelerate the development of intrinsic objectives, Empowerment 0.41 0.66 we retrospectively compute potential objectives on pre-collected datasets of agent behavior, rather Table 1: We computed Pearson correlation coefficients of than optimizing them online, and compare them each intrinsic objective with task reward and human similarity by analyzing their correlations. We study input across 3 Atari games and Minecraft from over 2 billion entropy, information gain, and empowerment time steps. The intrinsic objectives correlate more strongly across seven agents, three Atari games, and the 3D with human similarity than with task reward.

The drivers of compositionality in artificial languages that emerge when two (or more) agents play a non-visual referential game has been previously investigated using approaches based on the REINFORCE algorithm and the (Neural) Iterated Learning Model. Following the more recent introduction of the \textit{Straight-Through Gumbel-Softmax} (ST-GS) approach, this paper investigates to what extent the drivers of compositionality identified so far in the field apply in the ST-GS context and to what extent do they translate into (emergent) systematic generalisation abilities, when playing a visual referential game. Compositionality and the generalisation abilities of the emergent languages are assessed using topographic similarity and zero-shot compositional tests. Firstly, we provide evidence that the test-train split strategy significantly impacts the zero-shot compositional tests when dealing with visual stimuli, whilst it does not when dealing with symbolic ones. Secondly, empirical evidence shows that using the ST-GS approach with small batch sizes and an overcomplete communication channel improves compositionality in the emerging languages. Nevertheless, while shown robust with symbolic stimuli, the effect of the batch size is not so clear-cut when dealing with visual stimuli. Our results also show that not all overcomplete communication channels are created equal. Indeed, while increasing the maximum sentence length is found to be beneficial to further both compositionality and generalisation abilities, increasing the vocabulary size is found detrimental. Finally, a lack of correlation between the language compositionality at training-time and the agents' generalisation abilities is observed in the context of discriminative referential games with visual stimuli. This is similar to previous observations in the field using the generative variant with symbolic stimuli.

This work investigates the problem of multi-agents trajectory prediction. Prior approaches lack of capability of capturing fine-grained dependencies among coordinated agents. In this paper, we propose a spatial-temporal trajectory prediction approach that is able to learn the strategy of a team with multiple coordinated agents. In particular, we use graph-based attention model to learn the dependency of the agents. In addition, instead of utilizing the recurrent networks (e.g., VRNN, LSTM), our method uses a Temporal Convolutional Network (TCN) as the sequential model to support long effective history and provide important features such as parallelism and stable gradients. We demonstrate the validation and effectiveness of our approach on two different sports game datasets: basketball and soccer datasets. The result shows that compared to related approaches, our model that infers the dependency of players yields substantially improved performance. Code is available at https://github.com/iHeartGraph/predict

Bayesian optimisation presents a sample-efficient methodology for global optimisation. Within this framework, a crucial performance-determining subroutine is the maximisation of the acquisition function, a task complicated by the fact that acquisition functions tend to be non-convex and thus nontrivial to optimise. In this paper, we undertake a comprehensive empirical study of approaches to maximise the acquisition function. Additionally, by deriving novel, yet mathematically equivalent, compositional forms for popular acquisition functions, we recast the maximisation task as a compositional optimisation problem, allowing us to benefit from the extensive literature in this field. We highlight the empirical advantages of the compositional approach to acquisition function maximisation across 3958 individual experiments comprising synthetic optimisation tasks as well as tasks from Bayesmark. Given the generality of the acquisition function maximisation subroutine, we posit that the adoption of compositional optimisers has the potential to yield performance improvements across all domains in which Bayesian optimisation is currently being applied.

We consider the problem of learning fair policies in (deep) cooperative multi-agent reinforcement learning (MARL). We formalize it in a principled way as the problem of optimizing a welfare function that explicitly encodes two important aspects of fairness: efficiency and equity. As a solution method, we propose a novel neural network architecture, which is composed of two sub-networks specifically designed for taking into account the two aspects of fairness. In experiments, we demonstrate the importance of the two sub-networks for fair optimization. Our overall approach is general as it can accommodate any (sub)differentiable welfare function. Therefore, it is compatible with various notions of fairness that have been proposed in the literature (e.g., lexicographic maximin, generalized Gini social welfare function, proportional fairness). Our solution method is generic and can be implemented in various MARL settings: centralized training and decentralized execution, or fully decentralized. Finally, we experimentally validate our approach in various domains and show that it can perform much better than previous methods.

We investigate Kantian equilibria in finite normal form games, a class of non-Nashian, morally motivated courses of action that was recently proposed in the economics literature. We highlight a number of problems with such equilibria, including computational intractability, a high price of miscoordination, and expensive/problematic extension to general normal form games. We point out that such a proper generalization will likely involve the concept of program equilibrium. Finally we propose some general, intuitive, computationally tractable, other-regarding equilibria related to Kantian equilibria, as well as a class of courses of action that interpolates between purely self-regarding and Kantian behavior.

Recent advances in Artificial Intelligence (AI) have revived the quest for agents able to acquire an open-ended repertoire of skills. However, although this ability is fundamentally related to the characteristics of human intelligence, research in this field rarely considers the processes that may have guided the emergence of complex cognitive capacities during the evolution of the species. Research in Human Behavioral Ecology (HBE) seeks to understand how the behaviors characterizing human nature can be conceived as adaptive responses to major changes in the structure of our ecological niche. In this paper, we propose a framework highlighting the role of environmental complexity in open-ended skill acquisition, grounded in major hypotheses from HBE and recent contributions in Reinforcement learning (RL). We use this framework to highlight fundamental links between the two disciplines, as well as to identify feedback loops that bootstrap ecological complexity and create promising research directions for AI researchers.

ColorShapeLinks is an AI board game competition framework specially designed for students and educators in videogame development, with openness and accessibility in mind. The competition is based on an arbitrarily-sized version of the Simplexity board game, the motto of which, "simple to learn, complex to master", is curiously also applicable to AI agents. ColorShapeLinks offers graphical and text-based frontends and a completely open and documented development framework built using industry standard tools and following software engineering best practices. ColorShapeLinks is not only a competition, but both a game and a framework which educators and students can extend and use to host their own competitions.

Driven by recent successes in two-player, zero-sum game solving and playing, artificial intelligence work on games has increasingly focused on algorithms that produce equilibrium-based strategies. However, this approach has been less effective at producing competent players in general-sum games or those with more than two players than in two-player, zero-sum games. An appealing alternative is to consider adaptive algorithms that ensure strong performance in hindsight relative to what could have been achieved with modified behavior. This approach also leads to a game-theoretic analysis, but in the correlated play that arises from joint learning dynamics rather than factored agent behavior at equilibrium. We develop and advocate for this hindsight rationality framing of learning in general sequential decision-making settings. To this end, we re-examine mediated equilibrium and deviation types in extensive-form games, thereby gaining a more complete understanding and resolving past misconceptions. We present a set of examples illustrating the distinct strengths and weaknesses of each type of equilibrium in the literature, and prove that no tractable concept subsumes all others. This line of inquiry culminates in the definition of the deviation and equilibrium classes that correspond to algorithms in the counterfactual regret minimization (CFR) family, relating them to all others in the literature. Examining CFR in greater detail further leads to a new recursive definition of rationality in correlated play that extends sequential rationality in a way that naturally applies to hindsight evaluation.