Despite significant recent advances in the field of Deep Reinforcement Learning (DRL), such methods typically incur high cost of training to learn effective policies, thus posing cost and safety challenges in many practical applications. To improve the learning efficiency of (D)RL methods, transfer learning (TL) has emerged as a promising approach to leverage prior experience on a source domain to speed learning on a new, but related, target domain. In this paper, we take a novel model-informed approach to TL in DRL by assuming that we have knowledge of both the source and target domain models (which would be the case in the prevalent setting of DRL with simulators). While directly solving either the source or target MDP via solution methods like value iteration is computationally prohibitive, we exploit the fact that if the target and source MDPs differ only due to a small structural change in their rewards, we can apply structured value iteration methods in a procedure we term ModelDiff to solve the much smaller target-source ``Diff'' MDP for a reasonable horizon. This ModelDiff approach can then be integrated into extensions of standard DRL algorithms like ModelDiff (MD) DQN, where it provides enhanced provable lower bound guidance to DQN that often speeds convergence for the positive transfer case while critically avoiding decelerated learning in the negative transfer case. Experiments show that MD-DQN matches or outperforms existing TL methods and baselines in both positive and negative transfer settings.

Xiaotian Liu, Ali Pesaranghader, Hanze Li, Punyaphat Sukcharoenchaikul, Jaehong Kim, Tanmana Sadhu, Hyejeong Jeon, Scott Sanner. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

The ability to actively acquire information is essential for open-world planning under partial observability and incomplete knowledge. However, most existing embodied AI systems either assume a known object category or rely on passive perception strategies that exhaustively gather object and relational information from the environment. Such a strategy becomes insufficient in visually complex open-world settings. For instance, a typical household may contain thousands of novel and uniquely configured objects, most of which are irrelevant to the agent’s current task. Consequently, open-world agents must be capable of actively identifying and prioritizing task-relevant objects to enable efficient and goal-directed knowledge acquisition. In this work, we introduce ActiveVOO, a novel zero-shot framework for open-world embodied planning that emphasizes object-centric active knowledge acquisition. ActiveVOO employs lifted regression to generate compact, first-order subgoal descriptions that identify task-relevant objects, and provides a principled mechanism to quantify the utility of sensing actions based on commonsense priors derived from LLMs and VLMs. We evaluate ActiveVOO on the visual ALFWorld benchmark, where it achieves substantial improvements over existing LLM- and VLM-based planning approaches, notably outperforming VLMs fine-tuned on ALFWorld data. This work establishes a principled foundation for developing embodied agents capable of actively and efficiently acquiring knowledge to plan and act in open-world environments.

Monte Carlo tree search (MCTS) has been gaining increasing popularity, and the success of AlphaGo has prompted a new trend of incorporating a value network and a policy network constructed with neural networks into MCTS, namely, NN-MCTS. In this work, motivated by the shortcomings of the widely used upper confidence bounds applied to trees (UCT) policy, we formulate the node selection problem in NN-MCTS as a multistage ranking and selection (R&S) problem and propose a node selection policy that efficiently allocates a limited search budget to maximize the probability of correctly selecting the best action at the root state. The value and policy networks in NN-MCTS further improve the performance of the proposed node selection policy by providing prior knowledge and guiding the selection of the final action, respectively. Numerical experiments on two board games and an OpenAI task demonstrate that the proposed method outperforms the UCT policy used in AlphaGo Zero and MuZero, implying the potential of constructing node selection policies in NN-MCTS with R&S procedures. History: Accepted by Bruno Tuffin, Area Editor for Simulation. Funding: This work was supported by the National Natural Science Foundation of China [Grants 72325007, 72250065, and 72022001], and a PKU-Boya Postdoctoral Fellowship 2406396158. Supplemental Material: The software that supports the findings of this study is available within the paper and its Supplemental Information ( https://pubsonline.informs.org/doi/suppl/10.1287/ijoc.2023.0307 ) as well as from the IJOC GitHub software repository ( https://github.com/INFORMSJoC/2023.0307 ). The complete IJOC Software and Data Repository is available at https://informsjoc.github.io/ .

Recent studies on deep ensembles have identified the sharpness of the local minima of individual learners and the diversity of the ensemble members as key factors in improving test-time performance. Building on this, our study investigates the interplay between sharpness and diversity within deep ensembles, illustrating their crucial role in robust generalization to both in-distribution (ID) and out-of-distribution (OOD) data. We discover a trade-off between sharpness and diversity: minimizing the sharpness in the loss landscape tends to diminish the diversity of individual members within the ensemble, adversely affecting the ensemble's improvement. The trade-off is justified through our rigorous theoretical analysis and verified empirically through extensive experiments. To address the issue of reduced diversity, we introduce SharpBalance, a novel training approach that balances sharpness and diversity within ensembles. Theoretically, we show that our training strategy achieves a better sharpness-diversity trade-off. Empirically, we conducted comprehensive evaluations in various data sets (CIFAR-10, CIFAR-100, TinyImageNet) and showed that SharpBalance not only effectively improves the sharpness-diversity trade-off but also significantly improves ensemble performance in ID and OOD scenarios.

Embodied agents face significant challenges when tasked with performing actions in diverse environments, particularly in generalizing across object types and executing suitable actions to accomplish tasks. Furthermore, agents should exhibit robustness, minimizing the execution of illegal actions. In this work, we present Egocentric Planning, an innovative approach that combines symbolic planning and Object-oriented POMDPs to solve tasks in complex environments, harnessing existing models for visual perception and natural language processing. We evaluated our approach in ALFRED, a simulated environment designed for domestic tasks, and demonstrated its high scalability, achieving an impressive 36.07\% unseen success rate in the ALFRED benchmark and winning the ALFRED challenge at CVPR Embodied AI workshop. Our method requires reliable perception and the specification or learning of a symbolic description of the preconditions and effects of the agent's actions, as well as what object types reveal information about others. It can naturally scale to solve new tasks beyond ALFRED, as long as they can be solved using the available skills. This work offers a solid baseline for studying end-to-end and hybrid methods that aim to generalize to new tasks, including recent approaches relying on LLMs, but often struggle to scale to long sequences of actions or produce robust plans for novel tasks.

In this article, we propose a unified framework to solve the following two challenging problems in incomplete multi-view representation learning: i) how to learn a consistent representation unifying different views, and ii) how to recover the missing views. To address the challenges, we provide an information theoretical framework under which the consistency learning and data recovery are treated as a whole. With the theoretical framework, we propose a novel objective function which jointly solves the aforementioned two problems and achieves a provable sufficient and minimal representation. In detail, the consistency learning is performed by maximizing the mutual information of different views through contrastive learning, and the missing views are recovered by minimizing the conditional entropy through dual prediction. To the best of our knowledge, this is one of the first works to theoretically unify the cross-view consistency learning and data recovery for representation learning. Extensive experimental results show that the proposed method remarkably outperforms 20 competitive multi-view learning methods on six datasets in terms of clustering, classification, and human action recognition. The code could be accessed from https://pengxi.me.