Ufuk Topcu’s research while affiliated with University of Texas at Austin and other places

Many continuous control problems can be formulated as sparse-reward reinforcement learning (RL) tasks. In principle, online RL methods can automatically explore the state space to solve each new task. However, discovering sequences of actions that lead to a non-zero reward becomes exponentially more difficult as the task horizon increases. Manually shaping rewards can accelerate learning for a fixed task, but it is an arduous process that must be repeated for each new environment. We introduce a systematic reward-shaping framework that distills the information contained in 1) a task-agnostic prior data set and 2) a small number of task-specific expert demonstrations, and then uses these priors to synthesize dense dynamics-aware rewards for the given task. This supervision substantially accelerates learning in our experiments, and we provide analysis demonstrating how the approach can effectively guide online learning agents to faraway goals.

Competition among news sources may encourage some sources to share fake news and misinformation to influence the public. While sharing misinformation may lead to a short-term gain in audience engagement, it may damage the reputation of these sources, resulting in a loss of audience. To understand the rationale behind sharing misinformation, we model the competition as a zero-sum sequential game, where each news source influences individuals based on its credibility-how trustworthy the public perceives it-and the individual's opinion and susceptibility. In this game, news sources can decide whether to share factual information to enhance their credibility or disseminate misinformation for greater immediate attention at the cost of losing credibility. We employ the quantal response equilibrium concept, which accounts for the bounded rationality of human decision-making, allowing for imperfect or probabilistic choices. Our analysis shows that the resulting equilibria for this game reproduce the credibility-bias distribution observed in real-world news sources, with hyper-partisan sources more likely to spread misinformation than centrist ones. It further illustrates that disseminating misinformation can polarize the public. Notably, our model reveals that when one player increases misinformation dissemination, the other player is likely to follow, exacerbating the spread of misinformation. We conclude by discussing potential strategies to mitigate the spread of fake news and promote a more factual and reliable information landscape.

Autonomous agents perceive and interpret their surroundings by integrating multimodal inputs, such as vision, audio, and LiDAR. These perceptual modalities support retrieval tasks, such as place recognition in robotics. However, current multimodal retrieval systems encounter difficulties when parts of the data are missing due to sensor failures or inaccessibility, such as silent videos or LiDAR scans lacking RGB information. We propose Any2Any-a novel retrieval framework that addresses scenarios where both query and reference instances have incomplete modalities. Unlike previous methods limited to the imputation of two modalities, Any2Any handles any number of modalities without training generative models. It calculates pairwise similarities with cross-modal encoders and employs a two-stage calibration process with conformal prediction to align the similarities. Any2Any enables effective retrieval across multimodal datasets, e.g., text-LiDAR and text-time series. It achieves a Recall@5 of 35% on the KITTI dataset, which is on par with baseline models with complete modalities.

Multimodal foundation models offer a promising framework for robotic perception and planning by processing sensory inputs to generate actionable plans. However, addressing uncertainty in both perception (sensory interpretation) and decision-making (plan generation) remains a critical challenge for ensuring task reliability. We present a comprehensive framework to disentangle, quantify, and mitigate these two forms of uncertainty. We first introduce a framework for uncertainty disentanglement, isolating perception uncertainty arising from limitations in visual understanding and decision uncertainty relating to the robustness of generated plans. To quantify each type of uncertainty, we propose methods tailored to the unique properties of perception and decision-making: we use conformal prediction to calibrate perception uncertainty and introduce Formal-Methods-Driven Prediction (FMDP) to quantify decision uncertainty, leveraging formal verification techniques for theoretical guarantees. Building on this quantification, we implement two targeted intervention mechanisms: an active sensing process that dynamically re-observes high-uncertainty scenes to enhance visual input quality and an automated refinement procedure that fine-tunes the model on high-certainty data, improving its capability to meet task specifications. Empirical validation in real-world and simulated robotic tasks demonstrates that our uncertainty disentanglement framework reduces variability by up to 40% and enhances task success rates by 5% compared to baselines. These improvements are attributed to the combined effect of both interventions and highlight the importance of uncertainty disentanglement which facilitates targeted interventions that enhance the robustness and reliability of autonomous systems.

Strategic coordination between autonomous agents and human partners under incomplete information can be modeled as turn-based cooperative games. We extend a turn-based game under incomplete information, the shared-control game, to allow players to take multiple actions per turn rather than a single action. The extension enables the use of multi-step intent, which we hypothesize will improve performance in long-horizon tasks. To synthesize cooperative policies for the agent in this extended game, we propose an approach featuring a memory module for a running probabilistic belief of the environment dynamics and an online planning algorithm called IntentMCTS. This algorithm strategically selects the next action by leveraging any communicated multi-step intent via reward augmentation while considering the current belief. Agent-to-agent simulations in the Gnomes at Night testbed demonstrate that IntentMCTS requires fewer steps and control switches than baseline methods. A human-agent user study corroborates these findings, showing an 18.52% higher success rate compared to the heuristic baseline and a 5.56% improvement over the single-step prior work. Participants also report lower cognitive load, frustration, and higher satisfaction with the IntentMCTS agent partner.

Common feedback strategies in multi-agent dynamic games require all players' state information to compute control strategies. However, in real-world scenarios, sensing and communication limitations between agents make full state feedback expensive or impractical, and such strategies can become fragile when state information from other agents is inaccurate. To this end, we propose a regularized dynamic programming approach for finding sparse feedback policies that selectively depend on the states of a subset of agents in dynamic games. The proposed approach solves convex adaptive group Lasso problems to compute sparse policies approximating Nash equilibrium solutions. We prove the regularized solutions' asymptotic convergence to a neighborhood of Nash equilibrium policies in linear-quadratic (LQ) games. We extend the proposed approach to general non-LQ games via an iterative algorithm. Empirical results in multi-robot interaction scenarios show that the proposed approach effectively computes feedback policies with varying sparsity levels. When agents have noisy observations of other agents' states, simulation results indicate that the proposed regularized policies consistently achieve lower costs than standard Nash equilibrium policies by up to 77% for all interacting agents whose costs are coupled with other agents' states.

We develop a method that integrates the tree of thoughts and multi-agent framework to enhance the capability of pre-trained language models in solving complex, unfamiliar games. The method decomposes game-solving into four incremental tasks -- game summarization, area selection, action extraction, and action validation -- each assigned to a specific language-model agent. By constructing a tree of thoughts, the method simulates reasoning paths and allows agents to collaboratively distill game representations and tactics, mitigating the limitations of language models in reasoning and long-term memorization. Additionally, an automated fine-tuning process further optimizes the agents' performance by ranking query-response pairs based on game outcomes, e.g., winning or losing. We apply the method to a non-cooperative game and demonstrate a 65 percent winning rate against benchmark algorithms, with an additional 10 percent improvement after fine-tuning. In contrast to existing deep learning algorithms for game solving that require millions of training samples, the proposed method consumes approximately 1000 training samples, highlighting its efficiency and scalability.

Although pre-trained language models can generate executable plans (e.g., programmatic policies) for solving robot tasks, the generated plans may violate task-relevant logical specifications due to the models' black-box nature. A significant gap remains between the language models' outputs and verifiable executions of plans. We develop a method to generate executable plans and formally verify them against task-relevant safety specifications. Given a high-level task description in natural language, the proposed method queries a language model to generate plans in the form of executable robot programs. It then converts the generated plan into an automaton-based representation, allowing formal verification of the automaton against the specifications. We prove that given a set of verified plans, the composition of these plans also satisfies the safety specifications. This proof ensures the safety of complex, multi-component plans, obviating the computation complexity of verifying the composed plan. We then propose an automated fine-tuning process that refines the language model to generate specification-compliant plans without the need for human labeling. The empirical results show a 30 percent improvement in the probability of generating plans that meet task specifications after fine-tuning.

In reinforcement learning, conducting task composition by forming cohesive, executable sequences from multiple tasks remains challenging. However, the ability to (de)compose tasks is a linchpin in developing robotic systems capable of learning complex behaviors. Yet, compositional reinforcement learning is beset with difficulties, including the high dimensionality of the problem space, scarcity of rewards, and absence of system robustness after task composition. To surmount these challenges, we view task composition through the prism of category theory—a mathematical discipline exploring structures and their compositional relationships. The categorical properties of Markov decision processes untangle complex tasks into manageable sub-tasks, allowing for strategical reduction of dimensionality, facilitating more tractable reward structures, and bolstering system robustness. Experimental results support the categorical theory of reinforcement learning by enabling skill reduction, reuse, and recycling when learning complex robotic arm tasks.