This is a well-written and presented paper proposing a new framework for modeling animal behavior during a foraging task, and should be of interest to the NeurIPS audience. After rebuttal, 3 of the reviewers recommended accept based on it providing a nice link between the behavioral economics and reinforcement learning communities, and its strengths in both theory and empirical results. Therefore, I tentatively recommend accept. That said, during the discussions some concerns were brought up regarding some missing related work. I urge the authors to consider discussing in their final version several related works that R4, and I think are quite relevant: Daw et al, 2002, Neural Networks; Schwighofer & Doya 2003, Neural Networks; Niv et al 2006/2007 (and related), and also some works from motivation modeling literature (that R2 mentions in their review).

Artificial intelligence commonly refers to the science and engineering of artificial systems that can carry out tasks generally associated with requiring aspects of human intelligence, such as playing games, translating languages, and driving cars. In recent years, there have been exciting advances in learning-based, data-driven approaches towards AI, and machine learning and deep learning have enabled computer systems to perceive the world in unprecedented ways. Reinforcement learning has enabled breakthroughs in complex games such as Go and challenging robotics tasks such as quadrupedal locomotion. A key aspect of intelligence is to not only make predictions, but reason about the uncertainty in these predictions, and to consider this uncertainty when making decisions. This is what this manuscript on "Probabilistic Artificial Intelligence" is about. The first part covers probabilistic approaches to machine learning. We discuss the differentiation between "epistemic" uncertainty due to lack of data and "aleatoric" uncertainty, which is irreducible and stems, e.g., from noisy observations and outcomes. We discuss concrete approaches towards probabilistic inference and modern approaches to efficient approximate inference. The second part of the manuscript is about taking uncertainty into account in sequential decision tasks. We consider active learning and Bayesian optimization -- approaches that collect data by proposing experiments that are informative for reducing the epistemic uncertainty. We then consider reinforcement learning and modern deep RL approaches that use neural network function approximation. We close by discussing modern approaches in model-based RL, which harness epistemic and aleatoric uncertainty to guide exploration, while also reasoning about safety.

In this paper, we introduce DobLIX, a dual-objective learned index specifically designed for Log-Structured Merge(LSM) tree-based key-value stores. Although traditional learned indexes focus exclusively on optimizing index lookups, they often overlook the impact of data access from storage, resulting in performance bottlenecks. DobLIX addresses this by incorporating a second objective, data access optimization, into the learned index training process. This dual-objective approach ensures that both index lookup efficiency and data access costs are minimized, leading to significant improvements in read performance while maintaining write efficiency in real-world LSM-tree systems. Additionally, DobLIX features a reinforcement learning agent that dynamically tunes the system parameters, allowing it to adapt to varying workloads in real-time. Experimental results using real-world datasets demonstrate that DobLIX reduces indexing overhead and improves throughput by 1.19 to 2.21 times compared to state-of-the-art methods within RocksDB, a widely used LSM-tree-based storage engine.

We examine the problem of learning sequential tasks from a single visual demonstration. A key challenge arises when demonstrations are temporally misaligned due to variations in timing, differences in embodiment, or inconsistencies in execution. Existing approaches treat imitation as a distribution-matching problem, aligning individual frames between the agent and the demonstration. However, we show that such frame-level matching fails to enforce temporal ordering or ensure consistent progress. Our key insight is that matching should instead be defined at the level of sequences. We propose that perfect matching occurs when one sequence successfully covers all the subgoals in the same order as the other sequence. We present ORCA (ORdered Coverage Alignment), a dense per-timestep reward function that measures the probability of the agent covering demonstration frames in the correct order. On temporally misaligned demonstrations, we show that agents trained with the ORCA reward achieve $4.5$x improvement ($0.11 \rightarrow 0.50$ average normalized returns) for Meta-world tasks and $6.6$x improvement ($6.55 \rightarrow 43.3$ average returns) for Humanoid-v4 tasks compared to the best frame-level matching algorithms. We also provide empirical analysis showing that ORCA is robust to varying levels of temporal misalignment. Our code is available at https://github.com/portal-cornell/orca/

One of the most basic problems in reinforcement learning (RL) is policy evaluation: estimating the long-term return, i.e., value function, corresponding to a given fixed policy. The celebrated Temporal Difference (TD) learning algorithm addresses this problem, and recent work has investigated finite-time convergence guarantees for this algorithm and variants thereof. However, these guarantees hinge on the reward observations being always generated from a well-behaved (e.g., sub-Gaussian) true reward distribution. Motivated by harsh, real-world environments where such an idealistic assumption may no longer hold, we revisit the policy evaluation problem from the perspective of adversarial robustness. In particular, we consider a Huber-contaminated reward model where an adversary can arbitrarily corrupt each reward sample with a small probability $\epsilon$. Under this observation model, we first show that the adversary can cause the vanilla TD algorithm to converge to any arbitrary value function. We then develop a novel algorithm called Robust-TD and prove that its finite-time guarantees match that of vanilla TD with linear function approximation up to a small $O(\epsilon)$ term that captures the effect of corruption. We complement this result with a minimax lower bound, revealing that such an additive corruption-induced term is unavoidable. To our knowledge, these results are the first of their kind in the context of adversarial robustness of stochastic approximation schemes driven by Markov noise. The key new technical tool that enables our results is an analysis of the Median-of-Means estimator with corrupted, time-correlated data that might be of independent interest to the literature on robust statistics.

Multi-Agent Reinforcement Learning (MARL) has recently emerged as a significant area of research. However, MARL evaluation often lacks systematic diversity, hindering a comprehensive understanding of algorithms' capabilities. In particular, cooperative MARL algorithms are predominantly evaluated on benchmarks such as SMAC and GRF, which primarily feature team game scenarios without assessing adequately various aspects of agents' capabilities required in fully cooperative real-world tasks such as multi-robot cooperation and warehouse, resource management, search and rescue, and human-AI cooperation. Moreover, MARL algorithms are mainly evaluated on low dimensional state spaces, and thus their performance on high-dimensional (e.g., image) observations is not well-studied. To fill this gap, this paper highlights the crucial need for expanding systematic evaluation across a wider array of existing benchmarks. To this end, we conduct extensive evaluation and comparisons of well-known MARL algorithms on complex fully cooperative benchmarks, including tasks with images as agents' observations. Interestingly, our analysis shows that many algorithms, hailed as state-of-the-art on SMAC and GRF, may underperform standard MARL baselines on fully cooperative benchmarks. Finally, towards more systematic and better evaluation of cooperative MARL algorithms, we have open-sourced PyMARLzoo+, an extension of the widely used (E)PyMARL libraries, which addresses an open challenge from [TBG++21], facilitating seamless integration and support with all benchmarks of PettingZoo, as well as Overcooked, PressurePlate, Capture Target and Box Pushing.

As social robots become more common, many have adopted cute aesthetics aiming to enhance user comfort and acceptance. However, the effect of this aesthetic choice on human feedback in reinforcement learning scenarios remains unclear. Previous research has shown that humans tend to give more positive than negative feedback, which can cause failure to reach optimal robot behavior. We hypothesize that this positive bias may be exacerbated by the robot's level of perceived cuteness. To investigate, we conducted a user study where participants critique a robot's trajectories while it performs a task. We then analyzed the impact of the robot's aesthetic cuteness on the type of participant feedback. Our results suggest that there is a shift in the ratio of positive to negative feedback when perceived cuteness changes. In light of this, we experiment with a stochastic version of TAMER which adapts based on the user's level of positive feedback bias to mitigate these effects.

This paper investigates the anti-jamming channel access problem in complex and unknown jamming environments, where the jammer could dynamically adjust its strategies to target different channels. Traditional channel hopping anti-jamming approaches using fixed patterns are ineffective against such dynamic jamming attacks. Although the emerging deep reinforcement learning (DRL) based dynamic channel access approach could achieve the Nash equilibrium under fast-changing jamming attacks, it requires extensive training episodes. To address this issue, we propose a fast adaptive anti-jamming channel access approach guided by the intuition of ``learning faster than the jammer", where a synchronously updated coarse-grained spectrum prediction serves as an auxiliary task for the deep Q learning (DQN) based anti-jamming model. This helps the model identify a superior Q-function compared to standard DRL while significantly reducing the number of training episodes. Numerical results indicate that the proposed approach significantly accelerates the rate of convergence in model training, reducing the required training episodes by up to 70% compared to standard DRL. Additionally, it also achieves a 10% improvement in throughput over NE strategies, owing to the effective use of coarse-grained spectrum prediction.

The advancement in autonomous vehicles has empowered navigation and exploration in unknown environments. Geomagnetic navigation for autonomous vehicles has drawn increasing attention with its independence from GPS or inertial navigation devices. While geomagnetic navigation approaches have been extensively investigated, the generalizability of learned geomagnetic navigation strategies remains unexplored. The performance of a learned strategy can degrade outside of its source domain where the strategy is learned, due to a lack of knowledge about the geomagnetic characteristics in newly entered areas. This paper explores the generalization of learned geomagnetic navigation strategies via deep reinforcement learning (DRL). Particularly, we employ DRL agents to learn multiple teacher models from distributed domains that represent dispersed navigation strategies, and amalgamate the teacher models for generalizability across navigation areas. We design a reward shaping mechanism in training teacher models where we integrate both potential-based and intrinsic-motivated rewards. The designed reward shaping can enhance the exploration efficiency of the DRL agent and improve the representation of the teacher models. Upon the gained teacher models, we employ multi-teacher policy distillation to merge the policies learned by individual teachers, leading to a navigation strategy with generalizability across navigation domains. We conduct numerical simulations, and the results demonstrate an effective transfer of the learned DRL model from a source domain to new navigation areas. Compared to existing evolutionary-based geomagnetic navigation methods, our approach provides superior performance in terms of navigation length, duration, heading deviation, and success rate in cross-domain navigation. Geomagnetic navigation leverages the ubiquitous earth magnetic field signals for the navigation [1], [2], without independence on dedicated devices along the navigation route [3]-[5]. Geomagnetic navigation thus can secure the navigation mission, e.g., in remote areas or underwater environments where there GPS or pre-deployed navigation devices is unavailable [6].

In cooperative multi-agent reinforcement learning (MARL), learning effective policies is challenging when global rewards are sparse and delayed. This difficulty arises from the need to assign credit across both agents and time steps, a problem that existing methods often fail to address in episodic, long-horizon tasks. We propose Temporal-Agent Reward Redistribution $TAR^2$, a novel approach that decomposes sparse global rewards into agent-specific, time-step-specific components, thereby providing more frequent and accurate feedback for policy learning. Theoretically, we show that $TAR^2$ (i) aligns with potential-based reward shaping, preserving the same optimal policies as the original environment, and (ii) maintains policy gradient update directions identical to those under the original sparse reward, ensuring unbiased credit signals. Empirical results on two challenging benchmarks, SMACLite and Google Research Football, demonstrate that $TAR^2$ significantly stabilizes and accelerates convergence, outperforming strong baselines like AREL and STAS in both learning speed and final performance. These findings establish $TAR^2$ as a principled and practical solution for agent-temporal credit assignment in sparse-reward multi-agent systems.