Policy-Space Response Oracles (PSRO) as a general algorithmic framework has achieved state-of-the-art performance in learning equilibrium policies of two-player zero-sum games. However, the hand-crafted hyperparameter value selection in most of the existing works requires extensive domain knowledge, forming the main barrier to applying PSRO to different games. In this work, we make the first attempt to investigate the possibility of self-adaptively determining the optimal hyperparameter values in the PSRO framework. Our contributions are three-fold: (1) Using several hyperparameters, we propose a parametric PSRO that unifies the gradient descent ascent (GDA) and different PSRO variants. (2) We propose the self-adaptive PSRO (SPSRO) by casting the hyperparameter value selection of the parametric PSRO as a hyperparameter optimization (HPO) problem where our objective is to learn an HPO policy that can self-adaptively determine the optimal hyperparameter values during the running of the parametric PSRO. (3) To overcome the poor performance of online HPO methods, we propose a novel offline HPO approach to optimize the HPO policy based on the Transformer architecture. Experiments on various two-player zero-sum games demonstrate the superiority of SPSRO over different baselines.

Creating autonomous virtual agents capable of using arbitrary software on any digital device remains a major challenge for artificial intelligence. Two key obstacles hinder progress: insufficient infrastructure for building virtual agents in real-world environments, and the need for in-the-wild evaluation of fundamental agent abilities. To address this, we introduce AgentStudio, an online, realistic, and multimodal toolkit that covers the entire lifecycle of agent development. This includes environment setups, data collection, agent evaluation, and visualization. The observation and action spaces are highly generic, supporting both function calling and human-computer interfaces. This versatility is further enhanced by AgentStudio's graphical user interfaces, which allow efficient development of datasets and benchmarks in real-world settings. To illustrate, we introduce a visual grounding dataset and a real-world benchmark suite, both created with our graphical interfaces. Furthermore, we present several actionable insights derived from AgentStudio, e.g., general visual grounding, open-ended tool creation, learning from videos, etc. We have open-sourced the environments, datasets, benchmarks, and interfaces to promote research towards developing general virtual agents for the future.

Two-team zero-sum games are one of the most important paradigms in game theory. In this paper, we focus on finding an unexploitable equilibrium in large team games. An unexploitable equilibrium is a worst-case policy, where members in the opponent team cannot increase their team reward by taking any policy, e.g., cooperatively changing to other joint policies. As an optimal unexploitable equilibrium in two-team zero-sum games, correlated-team maxmin equilibrium remains unexploitable even in the worst case where players in the opponent team can achieve arbitrary cooperation through a joint team policy. However, finding such an equilibrium in large games is challenging due to the impracticality of evaluating the exponentially large number of joint policies. To solve this problem, we first introduce a general solution concept called restricted correlated-team maxmin equilibrium, which solves the problem of being impossible to evaluate all joint policy by a sample factor while avoiding an exploitation problem under the incomplete joint policy evaluation. We then develop an efficient sequential correlation mechanism, and based on which we propose an algorithm for approximating the unexploitable equilibrium in large games. We show that our approach achieves lower exploitability than the state-of-the-art baseline when encountering opponent teams with different exploitation ability in large team games including Google Research Football.

Despite the impressive performance across numerous tasks, large language models (LLMs) often fail in solving simple decision-making tasks due to the misalignment of the knowledge in LLMs with environments. On the contrary, reinforcement learning (RL) agents learn policies from scratch, which makes them always align with environments but difficult to incorporate prior knowledge for efficient explorations. To narrow the gap, we propose TWOSOME, a novel general online framework that deploys LLMs as decision-making agents to efficiently interact and align with embodied environments via RL without requiring any prepared datasets or prior knowledge of the environments. Firstly, we query the joint probabilities of each valid action with LLMs to form behavior policies. Then, to enhance the stability and robustness of the policies, we propose two normalization methods and summarize four prompt design principles. Finally, we design a novel parameter-efficient training architecture where the actor and critic share one frozen LLM equipped with low-rank adapters (LoRA) updated by PPO. We conduct extensive experiments to evaluate TWOSOME. i) TWOSOME exhibits significantly better sample efficiency and performance compared to the conventional RL method, PPO, and prompt tuning method, SayCan, in both classical decision-making environment, Overcooked, and simulated household environment, VirtualHome. ii) Benefiting from LLMs' open-vocabulary feature, TWOSOME shows superior generalization ability to unseen tasks. iii) Under our framework, there is no significant loss of the LLMs' original ability during online PPO finetuning.

Learning with noisy labels aims to ensure model generalization given a label-corrupted training set. The sample selection strategy achieves promising performance by selecting a label-reliable subset for model training. In this paper, we empirically reveal that existing sample selection methods suffer from both data and training bias that are represented as imbalanced selected sets and accumulation errors in practice, respectively. However, only the training bias was handled in previous studies. To address this limitation, we propose a noIse-Tolerant Expert Model (ITEM) for debiased learning in sample selection. Specifically, to mitigate the training bias, we design a robust network architecture that integrates with multiple experts. Compared with the prevailing double-branch network, our network exhibits better performance of selection and prediction by ensembling these experts while training with fewer parameters. Meanwhile, to mitigate the data bias, we propose a mixed sampling strategy based on two weight-based data samplers. By training on the mixture of two class-discriminative mini-batches, the model mitigates the effect of the imbalanced training set while avoiding sparse representations that are easily caused by sampling strategies. Extensive experiments and analyses demonstrate the effectiveness of ITEM. Our code is available at this url \href{https://github.com/1998v7/ITEM}{ITEM}.

Building agents with large language models (LLMs) for computer control is a burgeoning research area, where the agent receives computer states and performs actions to complete complex tasks. Previous computer agents have demonstrated the benefits of in-context learning (ICL); however, their performance is hindered by several issues. First, the limited context length of LLMs and complex computer states restrict the number of exemplars, as a single webpage can consume the entire context. Second, the exemplars in current methods, such as high-level plans and multi-choice questions, cannot represent complete trajectories, leading to suboptimal performance in long-horizon tasks. Third, existing computer agents rely on task-specific exemplars and overlook the similarity among tasks, resulting in poor generalization to novel tasks. To address these challenges, we introduce Synapse, a computer agent featuring three key components: i) state abstraction, which filters out task-irrelevant information from raw states, allowing more exemplars within the limited context, ii) trajectory-as-exemplar prompting, which prompts the LLM with complete trajectories of the abstracted states and actions to improve multi-step decision-making, and iii) exemplar memory, which stores the embeddings of exemplars and retrieves them via similarity search for generalization to novel tasks. We evaluate Synapse on MiniWoB++, a standard task suite, and Mind2Web, a real-world website benchmark. In MiniWoB++, Synapse achieves a 99.2% average success rate (a 10% relative improvement) across 64 tasks using demonstrations from only 48 tasks. Notably, Synapse is the first ICL method to solve the book-flight task in MiniWoB++. Synapse also exhibits a 56% relative improvement in average step success rate over the previous state-of-the-art prompting scheme in Mind2Web.

Estimating test accuracy without access to the ground-truth test labels under varying test environments is a challenging, yet extremely important problem in the safe deployment of machine learning algorithms. Existing works rely on the information from either the outputs or the extracted features of neural networks to formulate an estimation score correlating with the ground-truth test accuracy. In this paper, we investigate--both empirically and theoretically--how the information provided by the gradients can be predictive of the ground-truth test accuracy even under a distribution shift. Specifically, we use the norm of classification-layer gradients, backpropagated from the cross-entropy loss after only one gradient step over test data. Our key idea is that the model should be adjusted with a higher magnitude of gradients when it does not generalize to the test dataset with a distribution shift. We provide theoretical insights highlighting the main ingredients of such an approach ensuring its empirical success. Extensive experiments conducted on diverse distribution shifts and model structures demonstrate that our method significantly outperforms state-of-the-art algorithms.

Large language models (LLMs) [1-5] have recently become the new darling of academia and industry due to their remarkable performance in a variety of natural language processing (NLP) tasks. With the blessing of techniques such as large-scale pre-training [6], instruction tuning [7], and reinforcement learning from human feedback (RLHF) [8, 9], existing pretrained LLMs have demonstrated unique capabilities in language understanding, generation, interaction, and reasoning. These powerful capabilities of LLMs also drive many emergent research topics (e.g., instruction learning [10], in-context learning [1], chain-of-thought prompting [11], etc.) to further investigate their huge potentials, and bring unlimited possibilities for humans to build advanced artificial intelligence systems. However, alongside these advancements, a pressing issue that plagues LLMs has been widely criticized as "hallucination", referred to as a phenomenon where LLMs tend to generate text that is incorrect, nonsensical, or not real [12]. To alleviate the phenomenon of "hallucination" during the generation of LLMs, a promising direction is to retrieve the factual knowledge that are highly relevant to the user query, and then guide LLMs to generate response according to the retrieved context, resulting in retrieval-augmented LMs [13, 14] that have recently demonstrated strong performance in knowledge intensive tasks, especially for knowledge-based question answering (KBQA). The workflow of existing retrieval-augmented LMs [15, 16] mainly relies on embedding-based retrieval methods, which will first encode various forms of knowledge base and also the user query into the same latent space, then use a semantic similarity metric to retrieve the top-K most relevant documents as prompt, and finally instruct LLMs to only use the provided context to answer the user query.

Core-selecting combinatorial auctions (CAs) restrict the auction result in the core such that no coalitions could improve their utilities by engaging in collusion. The minimum-revenue-core (MRC) rule is a widely used core-selecting payment rule to maximize the total utilities of all bidders. However, the MRC rule can suffer from severe unfairness since it ignores individuals' utilities. To address this limitation, we propose to explore the leximin principle to achieve fairness in core-selecting CAs since the leximin principle prefers to maximize the utility of the worst-off; the resulting bidder-leximin-optimal (BLO) payment rule is then theoretically analyzed and an effective algorithm is further provided to compute the BLO outcome. Moreover, we conduct extensive experiments to show that our algorithm returns fairer utility distributions and is faster than existing algorithms of core-selecting payment rules.

Portfolio management (PM) is a fundamental financial trading task, which explores the optimal periodical reallocation of capitals into different stocks to pursue long-term profits. Reinforcement learning (RL) has recently shown its potential to train profitable agents for PM through interacting with financial markets. However, existing work mostly focuses on fixed stock pools, which is inconsistent with investors' practical demand. Specifically, the target stock pool of different investors varies dramatically due to their discrepancy on market states and individual investors may temporally adjust stocks they desire to trade (e.g., adding one popular stocks), which lead to customizable stock pools (CSPs). Existing RL methods require to retrain RL agents even with a tiny change of the stock pool, which leads to high computational cost and unstable performance. To tackle this challenge, we propose EarnMore, a rEinforcement leARNing framework with Maskable stOck REpresentation to handle PM with CSPs through one-shot training in a global stock pool (GSP). Specifically, we first introduce a mechanism to mask out the representation of the stocks outside the target pool. Second, we learn meaningful stock representations through a self-supervised masking and reconstruction process. Third, a re-weighting mechanism is designed to make the portfolio concentrate on favorable stocks and neglect the stocks outside the target pool. Through extensive experiments on 8 subset stock pools of the US stock market, we demonstrate that EarnMore significantly outperforms 14 state-of-the-art baselines in terms of 6 popular financial metrics with over 40% improvement on profit.