Trajectory prediction is an essential step in the pipeline of an autonomous vehicle. Inaccurate or inconsistent predictions regarding the movement of agents in its surroundings lead to poorly planned maneuvers and potentially dangerous situations for the end-user. Current state-of-the-art deep-learning-based trajectory prediction models can achieve excellent accuracy on public datasets. However, when used in more complex, interactive scenarios, they often fail to capture important interdependencies between agents, leading to inconsistent predictions among agents in the traffic scene. Inspired by the efficacy of incorporating human preference into large language models, this work fine-tunes trajectory prediction models in multi-agent settings using preference optimization. By taking as input automatically calculated preference rankings among predicted futures in the fine-tuning process, our experiments--using state-of-the-art models on three separate datasets--show that we are able to significantly improve scene consistency while minimally sacrificing trajectory prediction accuracy and without adding any excess computational requirements at inference time.

However, aligning these policies with end-user preferences remains a challenge, particularly when the preferences are hard to specify. While reinforcement learning from human feedback (RLHF) has become the predominant mechanism for alignment in non-embodied domains like large language models, it has not seen the same success in aligning visuomotor policies due to the prohibitive amount of human feedback required to learn visual reward functions. To address this limitation, we propose Representation-Aligned Preference-based Learning (RAPL), an observation-only method for learning visual rewards from significantly less human preference feedback. Unlike traditional RLHF, RAPL focuses human feedback on fine-tuning pre-trained vision encoders to align with the end-user's visual representation and then constructs a dense visual reward via feature matching in this aligned representation space. We first validate RAPL through simulation experiments in the X-Magical benchmark and Franka Panda robotic manipulation, demonstrating that it can learn rewards aligned with human preferences, more efficiently uses preference data, and generalizes across robot embodiments. Finally, our hardware experiments align pre-trained Diffusion Policies for three object manipulation tasks. We find that RAPL can fine-tune these policies with 5x less real human preference data, taking the first step towards minimizing human feedback while maximizing visuomotor robot policy alignment. More details (e.g., videos) are at the project website.

Online learning in a decentralized two-sided matching markets, where the demand-side (players) compete to match with the supply-side (arms), has received substantial interest because it abstracts out the complex interactions in matching platforms (e.g. UpWork, TaskRabbit). However, past works assume that each arm knows their preference ranking over the players (one-sided learning), and each player aim to learn the preference over arms through successive interactions. Moreover, several (impractical) assumptions on the problem are usually made for theoretical tractability such as broadcast player-arm match Liu et al. (2020; 2021); Kong & Li (2023) or serial dictatorship Sankararaman et al. (2021); Basu et al. (2021); Ghosh et al. (2022). In this paper, we study a decentralized two-sided matching market, where we do not assume that the preference ranking over players are known to the arms apriori. Furthermore, we do not have any structural assumptions on the problem. We propose a multi-phase explore-then-commit type algorithm namely epoch-based CA-ETC (collision avoidance explore then commit) (\texttt{CA-ETC} in short) for this problem that does not require any communication across agents (players and arms) and hence decentralized. We show that for the initial epoch length of $T_{\circ}$ and subsequent epoch-lengths of $2^{l/\gamma} T_{\circ}$ (for the $l-$th epoch with $\gamma \in (0,1)$ as an input parameter to the algorithm), \texttt{CA-ETC} yields a player optimal expected regret of $\mathcal{O}\left(T_{\circ} (\frac{K \log T}{T_{\circ} \Delta^2})^{1/\gamma} + T_{\circ} (\frac{T}{T_{\circ}})^\gamma\right)$ for the $i$-th player, where $T$ is the learning horizon, $K$ is the number of arms and $\Delta$ is an appropriately defined problem gap. Furthermore, we propose a blackboard communication based baseline achieving logarithmic regret in $T$.

Automating robotic surgery via learning from demonstration (LfD) techniques is extremely challenging. This is because surgical tasks often involve sequential decision-making processes with complex interactions of physical objects and have low tolerance for mistakes. Prior works assume that all demonstrations are fully observable and optimal, which might not be practical in the real world. This paper introduces a sample-efficient method that learns a robust reward function from a limited amount of ranked suboptimal demonstrations consisting of partial-view point cloud observations. The method then learns a policy by optimizing the learned reward function using reinforcement learning (RL). We show that using a learned reward function to obtain a policy is more robust than pure imitation learning. We apply our approach on a physical surgical electrocautery task and demonstrate that our method can perform well even when the provided demonstrations are suboptimal and the observations are high-dimensional point clouds. Code and videos available here: https://sites.google.com/view/lfdinelectrocautery

Two-sided matching markets have been widely studied in the literature due to their rich applications. Since participants are usually uncertain about their preferences, online algorithms have recently been adopted to learn them through iterative interactions. \citet{wang2022bandit} initiate the study of this problem in a many-to-one setting with \textit{responsiveness}. However, their results are far from optimal and lack guarantees of incentive compatibility. An extension of \citet{kong2023player} to this more general setting achieves a near-optimal bound for player-optimal regret. Nevertheless, due to the substantial requirement for collaboration, a single player's deviation could lead to a huge increase in its own cumulative rewards and an $O(T)$ regret for others. In this paper, we aim to enhance the regret bound in many-to-one markets while ensuring incentive compatibility. We first propose the adaptively explore-then-deferred-acceptance (AETDA) algorithm for responsiveness setting and derive an $O(N\min\left\{N,K\right\}C\log T/\Delta^2)$ upper bound for player-optimal stable regret while demonstrating its guarantee of incentive compatibility, where $N$ represents the number of players, $K$ is the number of arms, $T$ denotes the time horizon, $C$ is arms' total capacities and $\Delta$ signifies the minimum preference gap among players. This result is a significant improvement over \citet{wang2022bandit}. And to the best of our knowledge, it constitutes the first player-optimal guarantee in matching markets that offers such robust assurances. We also consider broader \textit{substitutable} preferences, one of the most general conditions to ensure the existence of a stable matching and cover responsiveness. We devise an online DA (ODA) algorithm and establish an $O(NK\log T/\Delta^2)$ player-pessimal stable regret bound for this setting.

The problem of matching markets has been studied for a long time in the literature due to its wide range of applications. Finding a stable matching is a common equilibrium objective in this problem. Since market participants are usually uncertain of their preferences, a rich line of recent works study the online setting where one-side participants (players) learn their unknown preferences from iterative interactions with the other side (arms). Most previous works in this line are only able to derive theoretical guarantees for player-pessimal stable regret, which is defined compared with the players' least-preferred stable matching. However, under the pessimal stable matching, players only obtain the least reward among all stable matchings. To maximize players' profits, player-optimal stable matching would be the most desirable. Though \citet{basu21beyond} successfully bring an upper bound for player-optimal stable regret, their result can be exponentially large if players' preference gap is small. Whether a polynomial guarantee for this regret exists is a significant but still open problem. In this work, we provide a new algorithm named explore-then-Gale-Shapley (ETGS) and show that the optimal stable regret of each player can be upper bounded by $O(K\log T/\Delta^2)$ where $K$ is the number of arms, $T$ is the horizon and $\Delta$ is the players' minimum preference gap among the first $N+1$-ranked arms. This result significantly improves previous works which either have a weaker player-pessimal stable matching objective or apply only to markets with special assumptions. When the preferences of participants satisfy some special conditions, our regret upper bound also matches the previously derived lower bound.

Fair allocation of indivisible goods has attracted extensive attention over the last two decades, yielding numerous elegant algorithmic results and producing challenging open questions. The problem becomes much harder in the presence of strategic agents. Ideally, one would want to design truthful mechanisms that produce allocations with fairness guarantees. However, in the standard setting without monetary transfers, it is generally impossible to have truthful mechanisms that provide non-trivial fairness guarantees. Recently, Amanatidis et al. [2021] suggested the study of mechanisms that produce fair allocations in their equilibria. Specifically, when the agents have additive valuation functions, the simple Round-Robin algorithm always has pure Nash equilibria and the corresponding allocations are envy-free up to one good (EF1) with respect to the agents' true valuation functions. Following this agenda, we show that this outstanding property of the Round-Robin mechanism extends much beyond the above default assumption of additivity. In particular, we prove that for agents with cancelable valuation functions (a natural class that contains, e.g., additive and budget-additive functions), this simple mechanism always has equilibria and even its approximate equilibria correspond to approximately EF1 allocations with respect to the agents' true valuation functions. Further, we show that the approximate EF1 fairness of approximate equilibria surprisingly holds for the important class of submodular valuation functions as well, even though exact equilibria fail to exist!

We consider the problem of fairly allocating a set of indivisible goods to a set of strategic agents with additive valuation functions. We assume no monetary transfers and, therefore, a mechanism in our setting is an algorithm that takes as input the reported -- rather than the true -- values of the agents. Our main goal is to explore whether there exist mechanisms that have pure Nash equilibria for every instance and, at the same time, provide fairness guarantees for the allocations that correspond to these equilibria. We focus on two relaxations of envy-freeness, namely envy-freeness up to one good (EF1), and envy-freeness up to any good (EFX), and we positively answer the above question. In particular, we study two algorithms that are known to produce such allocations in the non-strategic setting: Round-Robin (EF1 allocations for any number of agents) and a cut-and-choose algorithm of Plaut and Roughgarden [SIAM Journal of Discrete Mathematics, 2020] (EFX allocations for two agents). For Round-Robin we show that all of its pure Nash equilibria induce allocations that are EF1 with respect to the underlying true values, while for the algorithm of Plaut and Roughgarden we show that the corresponding allocations not only are EFX but also satisfy maximin share fairness, something that is not true for this algorithm in the non-strategic setting! Further, we show that a weaker version of the latter result holds for any mechanism for two agents that always has pure Nash equilibria which all induce EFX allocations.