When robots share the same workspace with other intelligent agents (e.g., other robots or humans), they must be able to reason about the behaviors of their neighboring agents while accomplishing the designated tasks. In practice, frequently, agents do not exhibit absolutely rational behavior due to their limited computational resources. Thus, predicting the optimal agent behaviors is undesirable (because it demands prohibitive computational resources) and undesirable (because the prediction may be wrong). Motivated by this observation, we remove the assumption of perfectly rational agents and propose incorporating the concept of bounded rationality from an information-theoretic view into the game-theoretic framework. This allows the robots to reason other agents' sub-optimal behaviors and act accordingly under their computational constraints. Specifically, bounded rationality directly models the agent's information processing ability, which is represented as the KL-divergence between nominal and optimized stochastic policies, and the solution to the bounded-optimal policy can be obtained by an efficient importance sampling approach. Using both simulated and real-world experiments in multi-robot navigation tasks, we demonstrate that the resulting framework allows the robots to reason about different levels of rational behaviors of other agents and compute a reasonable strategy under its computational constraint.

We introduce BusyBoard, a toy-inspired robot learning environment that leverages a diverse set of articulated objects and inter-object functional relations to provide rich visual feedback for robot interactions. Based on this environment, we introduce a learning framework, BusyBot, which allows an agent to jointly acquire three fundamental capabilities (interaction, reasoning, and planning) in an integrated and self-supervised manner. With the rich sensory feedback provided by BusyBoard, BusyBot first learns a policy to efficiently interact with the environment; then with data collected using the policy, BusyBot reasons the inter-object functional relations through a causal discovery network; and finally by combining the learned interaction policy and relation reasoning skill, the agent is able to perform goal-conditioned manipulation tasks. We evaluate BusyBot in both simulated and real-world environments, and validate its generalizability to unseen objects and relations. Video is available at https://youtu.be/EJ98xBJZ9ek.

Multi-agent market simulation is an effective tool to investigate the impact of various trading strategies in financial markets. One way of designing a trading agent in simulated markets is through reinforcement learning where the agent is trained to optimize its cumulative rewards (e.g., maximizing profits, minimizing risk, improving equitability). While the agent learns a rational policy that optimizes the reward function, in reality, human investors are sub-rational with their decisions often differing from the optimal. In this work, we model human sub-rationality as resulting from two possible causes: psychological bias and computational limitation. We first examine the relationship between investor profits and their degree of sub-rationality, and create hand-crafted market scenarios to intuitively explain the sub-rational human behaviors. Through experiments, we show that our models successfully capture human sub-rationality as observed in the behavioral finance literature. We also examine the impact of sub-rational human investors on market observables such as traded volumes, spread and volatility. We believe our work will benefit research in behavioral finance and provide a better understanding of human trading behavior.

In this paper, we propose a novel design of a hybrid mobile robot with controllable stiffness and deformable shape. Compared to conventional mobile agents, our system can switch between rigid and compliant phases by solidifying or melting Field's metal in its structure and, thus, alter its shape through the motion of its active components. In the soft state, the robot's main body can bend into circular arcs, which enables it to conform to surrounding curved objects. This variable geometry of the robot creates new motion modes which cannot be described by standard (i.e., fixed geometry) models. To this end, we develop a unified mathematical model that captures the differential kinematics of both rigid and soft states. An optimised control strategy is further proposed to select the most appropriate phase states and motion modes needed to reach a target pose-shape configuration. The performance of our new method is validated with numerical simulations and experiments conducted on a prototype system. The simulation source code is available at https://github.com/Louashka/2sr-agent-simulation.git}{GitHub repository.

The cooperative Multi-A gent R einforcement Learning (MARL) with permutation invariant agents framework has achieved tremendous empirical successes in real-world applications. Unfortunately, the theoretical understanding of this MARL problem is lacking due to the curse of many agents and the limited exploration of the relational reasoning in existing works. In this paper, we verify that the transformer implements complex relational reasoning, and we propose and analyze model-free and model-based offline MARL algorithms with the transformer approximators. We prove that the suboptimality gaps of the model-free and model-based algorithms are independent of and logarithmic in the number of agents respectively, which mitigates the curse of many agents. These results are consequences of a novel generalization error bound of the transformer and a novel analysis of the Maximum Likelihood Estimate (MLE) of the system dynamics with the transformer. Our model-based algorithm is the first provably efficient MARL algorithm that explicitly exploits the permutation invariance of the agents. Our improved generalization bound may be of independent interest and is applicable to other regression problems related to the transformer beyond MARL.

A recent line of work has established uncoupled learning dynamics such that, when employed by all players in a game, each player's \emph{regret} after $T$ repetitions grows polylogarithmically in $T$, an exponential improvement over the traditional guarantees within the no-regret framework. However, so far these results have only been limited to certain classes of games with structured strategy spaces -- such as normal-form and extensive-form games. The question as to whether $O(\text{polylog} T)$ regret bounds can be obtained for general convex and compact strategy sets -- which occur in many fundamental models in economics and multiagent systems -- while retaining efficient strategy updates is an important question. In this paper, we answer this in the positive by establishing the first uncoupled learning algorithm with $O(\log T)$ per-player regret in general \emph{convex games}, that is, games with concave utility functions supported on arbitrary convex and compact strategy sets. Our learning dynamics are based on an instantiation of optimistic follow-the-regularized-leader over an appropriately \emph{lifted} space using a \emph{self-concordant regularizer} that is, peculiarly, not a barrier for the feasible region. Further, our learning dynamics are efficiently implementable given access to a proximal oracle for the convex strategy set, leading to $O(\log\log T)$ per-iteration complexity; we also give extensions when access to only a \emph{linear} optimization oracle is assumed. Finally, we adapt our dynamics to guarantee $O(\sqrt{T})$ regret in the adversarial regime. Even in those special cases where prior results apply, our algorithm improves over the state-of-the-art regret bounds either in terms of the dependence on the number of iterations or on the dimension of the strategy sets.

In this paper, we present a novel approach to epistemic planning called planning with perspectives (PWP) that is both more expressive and computationally more efficient than existing state-of-the-art epistemic planning tools. Epistemic planning — planning with knowledge and belief — is essential in many multi-agent and human-agent interaction domains. Most state-of-the-art epistemic planners solve epistemic planning problems by either compiling to propositional classical planning (for example, generating all possible knowledge atoms or compiling epistemic formulae to normal forms); or explicitly encoding Kripke-based semantics. However, these methods become computationally infeasible as problem sizes grow. In this paper, we decompose epistemic planning by delegating reasoning about epistemic formulae to an external solver. We do this by modelling the problem using Functional STRIPS, which is more expressive than standard STRIPS and supports the use of external, black-box functions within action models. Building on recent work that demonstrates the relationship between what an agent ‘sees’ and what it knows, we define the perspective of each agent using an external function, and build a solver for epistemic logic around this. Modellers can customise the perspective function of agents, allowing new epistemic logics to be defined without changing the planner. We ran evaluations on well-known epistemic planning benchmarks to compare an existing state-of-the-art planner, and on new scenarios that demonstrate the expressiveness of the PWP approach. The results show that our PWP planner scales significantly better than the state-of-the-art planner that we compared against, and can express problems more succinctly.

Learning-based methods have shown promising performance for accelerating motion planning, but mostly in the setting of static environments. For the more challenging problem of planning in dynamic environments, such as multi-arm assembly tasks and human-robot interaction, motion planners need to consider the trajectories of the dynamic obstacles and reason about temporal-spatial interactions in very large state spaces. We propose a GNN-based approach that uses temporal encoding and imitation learning with data aggregation for learning both the embeddings and the edge prioritization policies. Experiments show that the proposed methods can significantly accelerate online planning over state-of-the-art complete dynamic planning algorithms. The learned models can often reduce costly collision checking operations by more than 1000x, and thus accelerating planning by up to 95%, while achieving high success rates on hard instances as well.

We describe the orchestration of a decentralized swarm of rotary-wing UAV-relays, augmenting the coverage and service capabilities of a terrestrial base station. Our goal is to minimize the time-average service latencies involved in handling transmission requests from ground users under Poisson arrivals, subject to an average UAV power constraint. Equipped with rate adaptation to efficiently leverage air-to-ground channel stochastics, we first derive the optimal control policy for a single relay via a semi-Markov decision process formulation, with competitive swarm optimization for UAV trajectory design. Accordingly, we detail a multiscale decomposition of this construction: outer decisions on radial wait velocities and end positions optimize the expected long-term delay-power trade-off; consequently, inner decisions on angular wait velocities, service schedules, and UAV trajectories greedily minimize the instantaneous delay-power costs. Next, generalizing to UAV swarms via replication and consensus-driven command-and-control, this policy is embedded with spread maximization and conflict resolution heuristics. We demonstrate that our framework offers superior performance with respect to average service latencies and average per-UAV power consumption: 11x faster data payload delivery relative to static UAV-relay deployments and 2x faster than a deep-Q network solution; remarkably, one relay with our scheme outclasses three relays under a joint successive convex approximation policy by 62%.

Current end-to-end autonomous driving methods either run a controller based on a planned trajectory or perform control prediction directly, which have spanned two separately studied lines of research. Seeing their potential mutual benefits to each other, this paper takes the initiative to explore the combination of these two well-developed worlds. Specifically, our integrated approach has two branches for trajectory planning and direct control, respectively. The trajectory branch predicts the future trajectory, while the control branch involves a novel multi-step prediction scheme such that the relationship between current actions and future states can be reasoned. The two branches are connected so that the control branch receives corresponding guidance from the trajectory branch at each time step. The outputs from two branches are then fused to achieve complementary advantages. Our results are evaluated in the closed-loop urban driving setting with challenging scenarios using the CARLA simulator. Even with a monocular camera input, the proposed approach ranks first on the official CARLA Leaderboard, outperforming other complex candidates with multiple sensors or fusion mechanisms by a large margin.