How are the advantage relations between a set of agents playing a game organized and how do they reflect the structure of the game? In this paper, we illustrate "Principal Trade-off Analysis" (PTA), a decomposition method that embeds games into a low-dimensional feature space. We argue that the embeddings are more revealing than previously demonstrated by developing an analogy to Principal Component Analysis (PCA). PTA represents an arbitrary two-player zero-sum game as the weighted sum of pairs of orthogonal 2D feature planes. We show that the feature planes represent unique strategic trade-offs and truncation of the sequence provides insightful model reduction. We demonstrate the validity of PTA on a quartet of games (Kuhn poker, RPS+2, Blotto, and Pokemon). In Kuhn poker, PTA clearly identifies the trade-off between bluffing and calling. In Blotto, PTA identifies game symmetries, and specifies strategic trade-offs associated with distinct win conditions. These symmetries reveal limitations of PTA unaddressed in previous work. For Pokemon, PTA recovers clusters that naturally correspond to Pokemon types, correctly identifies the designed trade-off between those types, and discovers a rock-paper-scissor (RPS) cycle in the Pokemon generation type - all absent any specific information except game outcomes.

Multi-armed Bandit motivates methods with provable upper bounds on regret and also the counterpart lower bounds have been extensively studied in this context. Recently, Multi-agent Multi-armed Bandit has gained significant traction in various domains, where individual clients face bandit problems in a distributed manner and the objective is the overall system performance, typically measured by regret. While efficient algorithms with regret upper bounds have emerged, limited attention has been given to the corresponding regret lower bounds, except for a recent lower bound for adversarial settings, which, however, has a gap with let known upper bounds. To this end, we herein provide the first comprehensive study on regret lower bounds across different settings and establish their tightness. Specifically, when the graphs exhibit good connectivity properties and the rewards are stochastically distributed, we demonstrate a lower bound of order $O(\log T)$ for instance-dependent bounds and $\sqrt{T}$ for mean-gap independent bounds which are tight. Assuming adversarial rewards, we establish a lower bound $O(T^{\frac{2}{3}})$ for connected graphs, thereby bridging the gap between the lower and upper bound in the prior work. We also show a linear regret lower bound when the graph is disconnected. While previous works have explored these settings with upper bounds, we provide a thorough study on tight lower bounds.

Active Inference is a recent framework for modeling planning under uncertainty. Empirical and theoretical work have now begun to evaluate the strengths and weaknesses of this approach and how it might be improved. A recent extension - the sophisticated inference (SI) algorithm - improves performance on multi-step planning problems through recursive decision tree search. However, little work to date has been done to compare SI to other established planning algorithms. SI was also developed with a focus on inference as opposed to learning. The present paper has two aims. First, we compare performance of SI to Bayesian reinforcement learning (RL) schemes designed to solve similar problems. Second, we present an extension of SI - sophisticated learning (SL) - that more fully incorporates active learning during planning. SL maintains beliefs about how model parameters would change under the future observations expected under each policy. This allows a form of counterfactual retrospective inference in which the agent considers what could be learned from current or past observations given different future observations. To accomplish these aims, we make use of a novel, biologically inspired environment designed to highlight the problem structure for which SL offers a unique solution. Here, an agent must continually search for available (but changing) resources in the presence of competing affordances for information gain. Our simulations show that SL outperforms all other algorithms in this context - most notably, Bayes-adaptive RL and upper confidence bound algorithms, which aim to solve multi-step planning problems using similar principles (i.e., directed exploration and counterfactual reasoning). These results provide added support for the utility of Active Inference in solving this class of biologically-relevant problems and offer added tools for testing hypotheses about human cognition.

Game-theoretic inverse learning is the problem of inferring the players' objectives from their actions. We formulate an inverse learning problem in a Stackelberg game between a leader and a follower, where each player's action is the trajectory of a dynamical system. We propose an active inverse learning method for the leader to infer which hypothesis among a finite set of candidates describes the follower's objective function. Instead of using passively observed trajectories like existing methods, the proposed method actively maximizes the differences in the follower's trajectories under different hypotheses to accelerate the leader's inference. We demonstrate the proposed method in a receding-horizon repeated trajectory game. Compared with uniformly random inputs, the leader inputs provided by the proposed method accelerate the convergence of the probability of different hypotheses conditioned on the follower's trajectory by orders of magnitude.

The performance of robots in high-level tasks depends on the quality of their lower-level controller, which requires fine-tuning. However, the intrinsically nonlinear dynamics and controllers make tuning a challenging task when it is done by hand. In this paper, we present DiffTune, a novel, gradient-based automatic tuning framework. We formulate the controller tuning as a parameter optimization problem. Our method unrolls the dynamical system and controller as a computational graph and updates the controller parameters through gradient-based optimization. The gradient is obtained using sensitivity propagation, which is the only method for gradient computation when tuning for a physical system instead of its simulated counterpart. Furthermore, we use $\mathcal{L}_1$ adaptive control to compensate for the uncertainties (that unavoidably exist in a physical system) such that the gradient is not biased by the unmodelled uncertainties. We validate the DiffTune on a Dubin's car and a quadrotor in challenging simulation environments. In comparison with state-of-the-art auto-tuning methods, DiffTune achieves the best performance in a more efficient manner owing to its effective usage of the first-order information of the system. Experiments on tuning a nonlinear controller for quadrotor show promising results, where DiffTune achieves 3.5x tracking error reduction on an aggressive trajectory in only 10 trials over a 12-dimensional controller parameter space.

We present a novel perception model named Herd's Eye View (HEV) that adopts a global perspective derived from multiple agents to boost the decision-making capabilities of reinforcement learning (RL) agents in multi-agent environments, specifically in the context of game AI. The HEV approach utilizes cooperative perception to empower RL agents with a global reasoning ability, enhancing their decision-making. We demonstrate the effectiveness of the HEV within simulated game environments and highlight its superior performance compared to traditional ego-centric perception models. This work contributes to cooperative perception and multi-agent reinforcement learning by offering a more realistic and efficient perspective for global coordination and decision-making within game environments. Moreover, our approach promotes broader AI applications beyond gaming by addressing constraints faced by AI in other fields such as robotics. The code is available at https://github.com/andrewnash/Herds-Eye-View

Autonomous driving involves complex decision-making in highly interactive environments, requiring thoughtful negotiation with other traffic participants. While reinforcement learning provides a way to learn such interaction behavior, efficient learning critically depends on scalable state representations. Contrary to imitation learning methods, high-dimensional state representations still constitute a major bottleneck for deep reinforcement learning methods in autonomous driving. In this paper, we study the challenges of constructing bird's-eye-view representations for autonomous driving and propose a recurrent learning architecture for long-horizon driving. Our PPO-based approach, called RecurrDriveNet, is demonstrated on a simulated autonomous driving task in CARLA, where it outperforms traditional frame-stacking methods while only requiring one million experiences for efficient training. RecurrDriveNet causes less than one infraction per driven kilometer by interacting safely with other road users.

Purpose of Review: To effectively synthesise and analyse multi-robot behaviour, we require formal task-level models which accurately capture multi-robot execution. In this paper, we review modelling formalisms for multi-robot systems under uncertainty, and discuss how they can be used for planning, reinforcement learning, model checking, and simulation. Recent Findings: Recent work has investigated models which more accurately capture multi-robot execution by considering different forms of uncertainty, such as temporal uncertainty and partial observability, and modelling the effects of robot interactions on action execution. Other strands of work have presented approaches for reducing the size of multi-robot models to admit more efficient solution methods. This can be achieved by decoupling the robots under independence assumptions, or reasoning over higher level macro actions. Summary: Existing multi-robot models demonstrate a trade off between accurately capturing robot dependencies and uncertainty, and being small enough to tractably solve real world problems. Therefore, future research should exploit realistic assumptions over multi-robot behaviour to develop smaller models which retain accurate representations of uncertainty and robot interactions; and exploit the structure of multi-robot problems, such as factored state spaces, to develop scalable solution methods.

Multi-robot systems have become very popular in recent years because of their wide spectrum of applications, ranging from surveillance to cooperative payload transportation. Model Predictive Control (MPC) is a promising controller for multi-robot control because of its preview capability and ability to handle constraints easily. The performance of the MPC widely depends on many parameters, among which the prediction horizon is the major contributor. Increasing the prediction horizon beyond a limit drastically increases the computation cost. Tuning the value of the prediction horizon can be very time-consuming, and the tuning process must be repeated for every task. Moreover, instead of using a fixed horizon for an entire task, a better balance between performance and computation cost can be established if different prediction horizons can be employed for every robot at each time step. Further, for such variable prediction horizon MPC for multiple robots, on-demand collision avoidance is the key requirement. We propose Versatile On-demand Collision Avoidance (VODCA) strategy to comply with the variable horizon model predictive control. We also present a framework for learning the prediction horizon for the multi-robot system as a function of the states of the robots using the Soft Actor-Critic (SAC) RL algorithm. The results are illustrated and validated numerically for different multi-robot tasks.

We describe SH-SVL, a parameterized family of first-order distributed optimization algorithms that enable a network of agents to collaboratively calculate a decision variable that minimizes the sum of cost functions at each agent. These algorithms are self-healing in that their convergence to the correct optimizer can be guaranteed even if they are initialized randomly, agents join or leave the network, or local cost functions change. We also present simulation evidence that our algorithms are self-healing in the case of dropped communication packets. Our algorithms are the first single-Laplacian methods for distributed convex optimization to exhibit all of these characteristics. We achieve self-healing by sacrificing internal stability, a fundamental trade-off for single-Laplacian methods.