Multi-Objective Reinforcement Learning

Occupant comfort and grid-aware energy efficiency are competing objectives whose joint optimization depends critically on how reward functions are specified in deep reinforcement learning (DRL) controllers for buildings. Yet reward design remains largely ad hoc: comfort terms are either hand-tuned heuristics or simple temperature-deviation proxies without explicit grounding in thermal-comfort physics. We present PIRS (Physics-Informed Reward Shaping), which replaces these ad-hoc comfort proxies with the ISO 7730 Predicted Mean Vote (PMV) formulation inside a weighted multi-objective reward for Soft Actor-Critic (SAC). By anchoring the comfort signal in the ISO 7730 PMV formulation, PIRS improves reward interpretability and provides a standards-grounded comfort proxy without changing any other component of the learning pipeline. We evaluate PIRS in CityLearn v2.1.2 (challenge 2022 phase 1) with a central SAC agent trained for 50k steps over five random seeds, and compare against a rule-based controller (RBC), a manually engineered reward (E2), an energy-only reward (E3), and a naive temperature-deviation comfort reward (E4). District-level key performance indicators (KPIs), reported as ratios versus RBC, show that PIRS attains cost, carbon, and electricity metrics on par with the manual baseline while substantially outperforming non-physics-grounded designs -- particularly on load ramping (1.78x vs. ~2.4x RBC) and daily peak demand. All DRL policies remain above RBC at this training budget; we interpret this gap honestly and position PIRS as an interpretable, standards-aligned foundation for reward design rather than a claim of dominance over classical control at limited compute.

The open-ended generation in LLMs usually requires multi-dimensional rubrics to adequately assess quality and guide the improvement of reinforcement learning. However, a critical dilemma inherent in this training paradigm is the imbalanced reward polarization along different rubric dimensions. Under this bottleneck, even if LLMs achieve relatively high rewards after training, they may still exhibit severe deficiencies in certain dimensions, leading to a direct deterioration in user experience. To address this problem, we propose Focal Reward, a novel objective to automatically balance the training of reinforcement learning under rubric-based rewards. Specifically, we first leverage an inverse reward projection mechanism to estimate the saturation degree of each criterion in the rubric, which forms the basis to calibrate the reward direction. Then, the final objective is designed with an automatically reweighting coefficient for each criterion to achieve the fine-grained balancing. Extensive experiments across three model scales and six benchmarks demonstrate that our Focal Reward method outperforms the strongest static aggregation baseline in all 18 model-benchmark comparisons. Rollout, mechanism, and ablation analyses further show that these gains arise from online, saturation-aware reallocation toward rubrics that still have room for improvement.

Federated edge learning (FEEL) has recently emerged as a promising paradigm for achieving edge intelligence (EI) via enabling collaborative model training across edge devices while protecting data privacy. In this paper, we put forth an online optimization framework that jointly manages federated training and inference on resource-constrained edge devices. We introduce a tandem-queue-inspired conversion mechanism that bridges inference requests and training data, and further incorporate both data and model freshness into the accuracy formulation to capture temporal dynamics in real-world environments. To maximize inference accuracy while minimizing latency and energy consumption, the mode selections, communication, and computation resource allocations of edge devices are jointly optimized. We formulate this optimization as a multi-objective optimization problem, which is NP-hard and further complicated by the online setting. To address these challenges, we transform the problem into a multi-objective Markov decision process (MOMDP) and develop a constrained multi-objective proximal policy optimization (C-MOPPO) algorithm. Specifically, C-MOPPO first learns a set of policies with different preferences across three objectives, then leverages constrained policy optimization to enrich the Pareto front and obtain high-quality, dense solutions. Extensive experiments demonstrate that C-MOPPO achieves well-balanced trade-offs among objectives and significantly outperforms baselines under various system configurations.

Reinforcement Learning has become a standard paradigm for aligning Large Language Models with human intent and task requirements. While Group Relative Policy Optimization offers an efficient, value-model-free alternative to Proximal Policy Optimization, adapting it to real-world multi-reward settings remains challenging. Standard scalarization practices, such as Reward Combination and Advantage Combination, suffer from significant drawbacks: Reward Combination frequently generates advantages with excessively large squared magnitudes that lead to training instability, while Advantage Combination relies on static hyperparameters and ignores cross-objective correlations. To address these limitations, we propose Dynamic Variance-adaptive Advantage Optimization (DVAO), which dynamically adjusts combination weights based on the empirical reward variance of each objective within a rollout group, effectively up-weighting objectives with a stronger learning signal while suppressing noisy ones. We mathematically prove that DVAO maintains bounded advantage magnitudes for stable training and introduces a self-adaptive cross-objective regularization mechanism. Extensive experiments on mathematical reasoning and tool-use benchmarks using Qwen3 and Qwen2.5 models demonstrate that DVAO significantly outperforms baseline methods, achieving a superior multi-objective Pareto frontier and robust training stability.

Coordinating micro-robotic swarms in realistic, time-dependent fluid environments remains a major challenge for biomedical and environmental applications. We present a hybrid CFD-MO-MARL (Computational Fluid Dynamics-Multi Objective-Multi Agent Reinforcement Learning) framework that couples a high-fidelity incompressible Navier--Stokes solver with decentralized proximal policy optimization to learn swarm control policies in oscillatory flow. Sixteen magnetically actuated micro-robots were simulated to navigate a pulsatile arterial waveform within a 2 mm channel while jointly optimizing upstream progression, energy efficiency, and motion smoothness. Conflicting objectives are resolved using Projected Conflicting Gradient (PCGrad) surgery. Without PCGrad, energy and smoothness rewards collapse during training, demonstrating that gradient conflict resolution is essential for stable multi-objective learning. The converged policy achieves progress rewards of 6.5-7.0, energy efficiency of 0.63-0.65, and smoothness of 0.97-0.99, outperforming brute-force baselines by more than 8 reward units on the primary objective. Training reveals three emergent behaviors not encoded in the reward function: hydrodynamic throttling formations that reduce peak flow velocities, a cycle-synchronized ratchet mechanism that exploits flow reversals for upstream movement, and individualized final-approach strategies near the target boundary. These results demonstrate that physically realistic fluid--agent interactions can be integrated directly into multi-objective reinforcement learning, providing a scalable framework for micro-swarm control in biomedical navigation, environmental monitoring, and microfluidic systems.

The rapid growth of Electric Vehicle (EV) adoption challenges power distribution networks through peak load spikes, voltage instability, and transformer overloads from uncoordinated charging. While Model Predictive Control (MPC) and standard Reinforcement Learning (RL) methods have addressed these issues, existing approaches rarely treat real-time carbon intensity or fluctuating renewable energy (RE) availability as primary scheduling objectives, leaving substantial decarbonisation potential unrealised. This paper proposes an emission-aware RL strategy based on the Soft Actor Critic (SAC) algorithm, with a multi-objective reward that penalises carbon emissions, curtailed on-site renewables, and unmet user demand. The agent is trained within a unified benchmarking framework on the EV2Gym platform, incorporating behind-the-meter solar and wind profiles, time-varying EirGrid carbon intensity data, and realistic workplace EV behaviour across 25 Electric Vehicle Supply Equipment (EVSE) units. Nine control strategies, including heuristics, emission-aware MPC variants, and the proposed RL agent, are compared under five renewable penetration scenarios (0%-50%) over ten independent runs each. The RL agent achieves a carbon intensity as low as 23.96 grams of carbon dioxide per kilowatt-hour under 50% wind penetration, representing up to 87% emission reduction versus the uncontrolled baseline, and outperforms the external graph-based Power Distribution Network (PDN) benchmark. Transformer overload remains below 7 kWh across scenarios, against up to 1093 kWh for the As Fast As Possible (AFAP) heuristic, and renewable self-consumption reaches 52% under combined wind and solar supply. Embedding carbon intensity forecasts into the RL state and reward aligns charging with low-emission periods while preserving grid compliance and user satisfaction.

Language models must now generalize out of the box to novel environments and work inside inference-scaling search procedures, such as AlphaEvolve, that select rollouts with a variety of task-specific reward functions. Unfortunately, the standard paradigm of LLM post-training optimizes a pre-specified scalar reward, often leading current LLMs to produce low-entropy response distributions and thus to struggle at displaying the diversity that inference-time search will require. We propose Vector Policy Optimization (VPO), an RL algorithm that explicitly trains policies to anticipate diverse downstream reward functions and to produce diverse solutions. VPO exploits that rewards are often vector-valued in practice, like per-test-case correctness in code generation or, say, multiple different user personas or reward models. VPO is essentially a drop-in replacement for the GRPO advantage estimator, but it trains the LLM to output a set of solutions where individual solutions specialize to different trade-offs in the vector reward space. Across four tasks, VPO matches or beats the strongest scalar RL baselines on test-time search (e.g. pass@k and best@k), with the gap widening as the search budget grows. For evolutionary search, VPO models unlock problems that GRPO models cannot solve at all. As test-time search becomes more standardized, optimizing for diversity may need to become the default post-training objective.

Reinforcement learning with verifiable rewards (RLVR) has substantially improved the reasoning ability of LLMs, but often depends on external supervision from human annotations or gold-standard solutions. Reinforcement learning from internal feedback (RLIF) has recently emerged as a scalable unsupervised alternative, using signals extracted from the model itself. However, existing RLIF methods typically rely on a single internal reward, which can lead to reward hacking, entropy collapse, and degraded reasoning structure. We propose a multi-reward RLIF framework that decomposes the training signal into two complementary components: an answer-level reward based on cluster voting and a completion-level reward based on token-wise self-certainty. To combine these signals robustly, we apply GDPO-based normalization to reduce reward-scale imbalance. We further introduce KL-Cov regularization, which targets low-entropy token distributions responsible for disproportionate entropy reduction, preserving exploration and preventing late-stage collapse. Across mathematical reasoning and code-generation benchmarks, our method improves stability and robustness over prior unsupervised RL approaches, while achieving performance close to supervised RLVR methods. These results show that complementary internal rewards, combined with targeted regularization, can support stable long-horizon reasoning without relying on external ground-truth supervision. Code will be released soon.

Complex reinforcement learning environments frequently employ multi-task and mixed-reward formulations. In these settings, heterogeneous reward distributions and correlated reward dimensions often destabilize the construction of scalar advantages. To address these challenges, we propose Reward-Decorrelated Policy Optimization (RDPO), a reward-processing method designed to explicitly target both failure modes. RDPO first utilizes Magnitude-Aware Quantile normalization to stabilize prompt-level advantage allocation across binary, fractional, and continuous rewards. It then applies Mahalanobis whitening within each active reward subspace to mitigate correlation redundancy prior to aggregation. When applied during the post-training of LongCat-Flash, RDPO enhances instruction following, writing quality, and robustness to hard prompts while remaining broadly competitive on reasoning and coding evaluations.

Multi-objective reinforcement learning in robotic domains requires balancing complex, non-convex trade-offs between conflicting objectives. While linear scalarization methods provide stability, they are theoretically incapable of recovering solutions within non-convex regions of the Pareto front. Conversely, static non-linear scalarizations (e.g., Tchebycheff) can theoretically access these regions but often suffer from severe gradient variance and optimization instability in deep RL. In this work, we propose an Adaptive Smooth Tchebycheff framework that resolves this tension by dynamically modulating the curvature of the optimization landscape. We introduce a novel conflict-driven controller that regulates the optimization smoothness based on real-time gradient interference. This allows the agent to anneal toward precise, non-convex scalarization when objectives align, while elastically reverting to stable, smooth approximations when destructive gradient conflicts emerge. We validate our approach on a challenging robotic stealth visual search task -- a proxy for monitoring of protected/fragile ecosystems -- where an agent must balance search, exposure/interference minimization and exploration speed. Extensive ablations confirm that our conflict-aware adaptation enables the robust discovery of Pareto-optimal policies in non-convex regions inaccessible to linear baselines and unstable for static non-linear methods. Website: https://alejandromllo.github.io/research/pasta/

This work investigates multi-objective imitation learning: the problem of recovering policies that lie on the Pareto front given demonstrations from multiple Pareto-optimal experts in a Multi-Objective Markov Decision Process (MOMDP). Standard imitation approaches are ill-equipped for this regime, as naively aggregating conflicting expert trajectories can result in dominated policies. To address this, we introduce Multi-Output Augmented Behavioral Cloning (MA-BC), an algorithm that systematically partitions divergent expert data while pooling state-action pairs where no behavior conflict is observed. Theoretically, we prove that MA-BC converges to Pareto-optimal policies at a faster statistical rate than any learner that considers each expert dataset independently. Furthermore, we establish a novel lower bound for multi-objective imitation learning, demonstrating that MA-BC is minimax optimal. Finally, we empirically validate our algorithm across diverse discrete environments and, guided by our theoretical insights, extend and evaluate MA-BC on a continuous Linear Quadratic Regulator (LQR) control task.

Uncrewed aerial vehicles (UAVs) are increasingly deployed in complex networked environments, yet the joint optimization of multi-UAV motion control and connectivity remains a fundamental challenge. In this paper, we study a multi-UAV system operating in an integrated terrestrial and non-terrestrial network (ITNTN) comprising terrestrial base stations and high-altitude platform stations (HAPS). We consider a three-dimensional (3D) aerial highway scenario where UAVs must adapt their motion to ensure collision avoidance, efficient traffic flow, and reliable communication under dynamic and partially observable conditions. We first model the problem as a hierarchical multi-objective partially observable Markov decision process (H-MO-POMDP), capturing the coupling between control and communication objectives. Based on this formulation, we propose a large language model (LLM)-driven hierarchical multi-rate control framework. At the global level, an LLM-based controller on the HAPS performs long-term planning for load balancing and handover decisions. At the local level, each UAV employs a hybrid controller that integrates a slow-timescale LLM for high-level spatial reasoning with a reinforcement learning agent for faster UAV-to-infrastructure (U2I) communication and motion control. We further develop a high-fidelity 3D simulation platform by integrating the gym-pybullet-drones environment with 3GPP-compliant RF/THz channel models. Numerical results demonstrate that the proposed framework significantly outperforms state-of-the-art baselines, achieving a 14% increase in transportation efficiency and a 25% improvement in telecommunication throughput. Additionally, it achieves a 23% reduction in physical collision rates, demonstrating strong handover stability and zero-shot generalization in dynamic scenarios.

Multi-objective reinforcement learning (MORL) allows a user to express preference over outcomes in terms of the relative importance of the objectives, but standard metrics cannot capture whether changes in preference reliably change the agent's behavior in the intended way, a property termed controllability. As a result, preference-conditioned agents can score well on standard MORL metrics while being insensitive to the preference input. If the ability to control agents cannot be reliably assessed, the symbolic interface that MORL provides between user intent and agent behavior is broken. Mainstream MORL metrics alone fail to measure the controllability of preference-conditioned agents, motivating a complementary metric specifically designed to that end. We hope the results spur discussion in the community on existing evaluation protocols to consolidate advances in preference adaptation in MORL to larger and more complex problems.

Preference-conditioned multi-objective reinforcement learning aims to learn a single policy that captures trade-offs across preferences, but under nonlinear scalarization the uniqueness and continuity of the preference-to-solution correspondence remain unclear. We study this problem in tabular multi-objective Markov decision processes (MDPs) using smooth Tchebycheff scalarization as a monotone utility. Under mild interior conditions on the preference set, we prove that each preference induces a unique Pareto-optimal return vector and that this vector depends Lipschitz-continuously on the preference, providing a principled foundation for preference sweeping toward dense Pareto-front coverage. To compute these targets, we formulate the problem over occupancy measures and derive Concave Mirror Descent Policy Iteration (CMDPI), which achieves an $O(1/k)$ objective-suboptimality rate. We further show that each update is equivalent to solving a Kullback-Leibler-regularized MDP with the previous policy as reference, yielding a policy-iteration interpretation and finite-iterate policy continuity across preferences. We instantiate the update as a deep actor-critic algorithm preserving previous-policy regularization. On eight MO-Gymnasium tasks, it achieves the best average hypervolume rank among recent baselines and strong expected-utility performance. Continuous-control experiments indicate gains beyond the discrete-action setting.

Image captioning is one of the most fundamental tasks in computer vision. Owing to its open-ended nature, it has received significant attention in the era of multimodal large language models (MLLMs). In pursuit of ever more detailed and accurate captions, recent work has increasingly turned to reinforcement learning (RL). However, existing captioning-RL methods and evaluation metrics often emphasize a narrow notion of caption quality, inducing trade-offs across core dimensions of captioning. For example, utility-oriented objectives can encourage noisy, hallucinated, or overlong captions that improve downstream question answering while harming fluency, whereas arena-style objectives can favor fluent but generic descriptions with limited usefulness. To address this, we propose a more balanced RL framework that jointly optimizes utility-aware correctness, reference coverage, and linguistic quality. In order to effectively optimize the resulting continuous multi-objective reward formulation, we apply GDPO-style reward-decoupled normalization to continuous-valued captioning rewards and show that it improves performance over vanilla GRPO. Additionally, we introduce length-conditional reward masking, yielding a more suitable length penalty for captioning. Across LLaVA-1.5-7B and Qwen2.5-VL 3B and 7B base models, our method consistently improves caption quality, with peak gains of +13.6 DCScore, +9.0 CaptionQA, and +29.0 CapArena across different models.

Large-scale recommenders encode multi-objective trade-offs by combining multiple predicted outcomes into a single utility score. Although this utility layer can be updated independently of the ranker, weight tuning remains largely manual, globally applied, slow to adapt to changing environments and business needs, and hard to govern as priorities shift. We propose PRL-PUTS, a Production-ready, ranker independent RL framework for Personalized Utility-weight Tuning with Pareto Sweeping. We cast utility tuning as a one-step, value-based RL problem: given request context, an agent selects a utility-weight vector that re-weights ranker predictions to maximize request-level engagement rewards. To visualize performance across the trade-off spectrum and allow decision makers to update the deployed operating policy instantly, we adopt an inference-time Pareto frontier sweeping via a scalarization parameter, producing a family of policies and an empirical Pareto frontier used as a governance artifact for operating policy selection. PRL-PUTS runs in parallel with ranking inference without adding serving latency. We validate PRL-PUTS with offline analysis using unbiased exploration logs and online experiments on Pinterest Homefeed where PRL-PUTS showed significant increases in engagement compared to baseline such as +0.13% increase in successful session, a core metric for user engagement.

Reinforcement learning fine-tuning has become the dominant approach for aligning diffusion models with human preferences. However, assessing images is intrinsically a multi-dimensional task, and multiple evaluation criteria need to be optimized simultaneously. Existing practice deal with multiple rewards by training one specialist model per reward, optimizing a weighted-sum reward $R(x)=\sum_k w_k R_k(x)$, or sequentially fine-tuning with a hand-crafted stage schedule. These approaches either fail to produce a unified model that can be jointly trained on all rewards or necessitates heavy manually tuned sequential training. We find that the failure stems from using a naive weighted-sum reward aggregation. This approach suffers from a sample-level mismatch because most rollouts are specialist samples, highly informative for certain reward dimensions but irrelevant for others; consequently, weighted summation dilutes their supervision. To address this issue, we propose MARBLE (Multi-Aspect Reward BaLancE), a gradient-space optimization framework that maintains independent advantage estimators for each reward, computes per-reward policy gradients, and harmonizes them into a single update direction without manually-tuned reward weighting, by solving a Quadratic Programming problem. We further propose an amortized formulation that exploits the affine structure of the loss used in DiffusionNFT, to reduce the per-step cost from K+1 backward passes to near single-reward baseline cost, together with EMA smoothing on the balancing coefficients to stabilize updates against transient single-batch fluctuations. On SD3.5 Medium with five rewards, MARBLE improves all five reward dimensions simultaneously, turns the worst-aligned reward's gradient cosine from negative under weighted summation in 80% of mini-batches to consistently positive, and runs at 0.97X the training speed of baseline training.

In this paper, we propose a dueling double deep Q-network (DDQN)-based adaptive multi-objective handover framework for low Earth orbit (LEO) satellite networks. The proposed method enables dynamic trade-off learning among throughput, blocking probability, and switching cost under time-varying network conditions. Simulation results demonstrate that the proposed approach consistently outperforms conventional baselines, achieving up to 10.3% throughput improvement and near-zero blocking under typical operating conditions.

Designing therapeutic messenger RNA (mRNA) requires generating full-length transcripts that optimally balance intracellular stability and translation efficiency. While generative models have advanced mRNA design, existing approaches rely on region-wise generation, expensive inference-time search, or target-specific model updates. To overcome these limitations, we introduce ProMORNA, a zero-shot, end-to-end generative framework for full-length mRNA design. ProMORNA aligns the design process with modern Large Language Model training pipelines: it utilizes a BART-style architecture pre-trained on over 6 million natural protein-mRNA pairs, followed by a two-stage post-training process comprising cold-start supervised fine-tuning and multi-objective reinforcement learning. By standardizing and aggregating relative advantages at the individual metric level with domain-specific stabilization, our post-training stage directly aligns the generative policy with conflicting biological constraints while avoiding direct scalarization of raw objective scores. In silico evaluations demonstrate that ProMORNA pushes the Pareto frontier of predicted stability and translation efficiency beyond standard baselines and GEMORNA, a leading state-of-the-art method. In three independent in vitro Fluc2P experiments, Candidate 2 achieved a 12-72h reporter-activity AUC 3.33 times that of the conventional Benchmark (Holm-adjusted $P=0.01285$), while its estimated 1.29-fold advantage over the reported best GEMORNA candidate remained exploratory. These results support ProMORNA as a promising framework for generating functionally active full-length mRNA candidates.

Many sequential decision-making tasks involve optimizing multiple conflicting objectives, requiring policies that adapt to different user preferences. In multi-objective reinforcement learning (MORL), one widely studied approach} addresses this by training a single policy network conditioned on preference-weighted rewards. In this paper, we explore a novel algorithmic perspective: leveraging reward-free reinforcement learning (RFRL) for MORL. While RFRL has historically been studied independently of MORL, it learns optimal policies for any possible reward function, making it a natural fit for MORL's challenge of handling unknown user preferences. We propose using the RFRL's training objective as an auxiliary task to enhance MORL, enabling more effective knowledge sharing beyond the multi-objective reward function given at training time. To this end, we adapt a state-of-the-art RFRL algorithm to the MORL setting and introduce a preference-guided exploration strategy that focuses learning on relevant parts of the environment. Through extensive experiments and ablation studies, we demonstrate that our approach significantly outperforms the state-of-the-art MORL methods across diverse MO-Gymnasium tasks, achieving superior performance and data efficiency. This work provides the first systematic adaptation of RFRL to MORL, demonstrating its potential as a scalable and empirically effective solution to multi-objective policy learning.

Current visual text generation models struggle with the trade-off between text accuracy and overall image coherence. We find that achieving high text accuracy can reduce aesthetic quality and instruction-following capability. Although reinforcement learning approaches can alleviate the problem through aligning with multiple rewards, they are often unstable for text generation, as existing approaches normally optimize multiple rewards in a weighted-sum way. In addition, it is difficult to balance the weight of each reward. Moreover, reinforcement learning requires a set of training instructions. A large number of prompts require more training time and computing resources, while a small set leads to poor performance. Hence, how to select the prompts for efficient training is an unsolved problem. In this study, we propose Pareto-Optimal Curriculum Alignment (POCA), a framework that addresses this issue as a multi-objective problem by: 1) identifying the Pareto-optimal set to avoid simple scalarization and 2) designing an adaptive curriculum alignment strategy to manage a learning sequence of a multi-reward dataset using automatic difficulty assessment, which is crucial for optimal convergence as RL methods explore in a limited data environment. In synergy, POCA finds the Pareto-optimal set in a unified reward space, which eliminates inconsistent signals to find the best trade-off solution from different rewards under an easy-to-hard optimization landscape. The experimental results show that POCA significantly improves all metrics such as CLIP, HPS scores and sentence accuracy.

Reinforcement Learning (RL) post-training has become the standard for aligning generative models with human preferences, yet most methods rely on a single scalar reward. When multiple criteria matter, the prevailing practice of ``early scalarization'' collapses rewards into a fixed weighted sum. This commits the model to a single trade-off point at training time, providing no inference-time control over inherently conflicting goals -- such as prompt adherence versus source fidelity in image editing. We introduce ParetoSlider, a multi-objective RL (MORL) framework that trains a single diffusion model to approximate the entire Pareto front. By training the model with continuously varying preference weights as a conditioning signal, we enable users to navigate optimal trade-offs at inference time without retraining or maintaining multiple checkpoints. We evaluate ParetoSlider across three state-of-the-art flow-matching backbones: SD3.5, FluxKontext, and LTX-2. Our single preference-conditioned model matches or exceeds the performance of baselines trained separately for fixed reward trade-offs, while uniquely providing fine-grained control over competing generative goals.

Reinforcement learning, particularly Group Relative Policy Optimization (GRPO), has emerged as an effective framework for post-training visual generative models with human preference signals. However, its effectiveness is fundamentally limited by coarse reward credit assignment. In modern visual generation, multiple reward models are often used to capture heterogeneous objectives, such as visual quality, motion consistency, and text alignment. Existing GRPO pipelines typically collapse these rewards into a single static scalar and propagate it uniformly across the entire diffusion trajectory. This design ignores the stage-specific roles of different denoising steps and produces mistimed or incompatible optimization signals. To address this issue, we propose Objective-aware Trajectory Credit Assignment (OTCA), a structured framework for fine-grained GRPO training. OTCA consists of two key components. Trajectory-Level Credit Decomposition estimates the relative importance of different denoising steps. Multi-Objective Credit Allocation adaptively weights and combines multiple reward signals throughout the denoising process. By jointly modeling temporal credit and objective-level credit, OTCA converts coarse reward supervision into a structured, timestep-aware training signal that better matches the iterative nature of diffusion-based generation. Extensive experiments show that OTCA consistently improves both image and video generation quality across evaluation metrics.

This research note identifies a previously overlooked distinction between multi-objective reinforcement learning (MORL), and more conventional single-objective reinforcement learning (RL). It has previously been noted that the optimal policy for an MORL agent with a non-linear utility function is required to be conditioned on both the current environmental state and on some measure of the previously accrued reward. This is generally implemented by concatenating the observed state of the environment with the discounted sum of previous rewards to create an augmented state. While augmented states have been widely-used in the MORL literature, one implication of their use has not previously been reported -- namely that they require the agent to have continued access to the reward signal (or a proxy thereof) after deployment, even if no further learning is required. This note explains why this is the case, and considers the practical repercussions of this requirement.

Large language models can be aligned with human preferences through offline reinforcement learning (RL) on small labeled datasets. While single-objective alignment is well-studied, many real-world applications demand the simultaneous optimization of multiple conflicting rewards, e.g. activity and specificity for proteins, or helpfulness and harmlessness for chatbots. Prior work has largely relied on linear reward scalarization, which provably fails to recover non-convex regions of the Pareto front. In this paper, instead of scalarizing the rewards directly, we frame multi-objective RL itself as an optimization problem to be scalarized via smooth Tchebycheff scalarization, a recent technique that overcomes the drawbacks of linear scalarization. We use this formulation to derive Smooth Tchebycheff Optimization of Multi-Objective Preferences (STOMP), a novel offline RL algorithm that extends direct preference optimization to the multi-objective setting in a principled way by standardizing the individual rewards based on their observed distributions. We empirically validate STOMP using multiple base models on 3 protein engineering and 3 chatbot alignment datasets. Compared to state-of-the-art baselines, STOMP achieves or ties for the highest hypervolumes on 16/18 protein tasks and 5/6 natural language tasks. We thus demonstrate that STOMP is a powerful, robust multi-objective alignment algorithm that can meaningfully improve post-training in multiple domains.

This study presents a multi-agent reinforcement learning (MARL) framework for load-constrained wind farm flow control (WFFC). While wake steering can enhance total wind farm power, it often introduces increased structural loads on downstream turbines. To address this, we integrate an Independent Soft Actor-Critic (I-SAC) architecture with a data-driven, local inflow sector-averaged surrogate model to provide real-time estimates of Damage Equivalent Loads (DELs). By incorporating these estimates into a shaped reward function, turbine-specific agents are trained to maximize power production while adhering to specific load-increase thresholds ($Δ_{max}$) of 10%, 20%, and 30% relative to a baseline controller. The framework is implemented within the WindGym environment using the DYNAMIKS flow solver with Dynamic Wake Meandering (DWM) model to capture non-stationary wake physics. Results indicate that the MARL agents successfully learn collaborative policies that prioritise power gain while actively retreating from high-DEL control strategies.

Aligning large language models (LLMs) with human preferences is critical for enhancing LLMs' safety, helpfulness, humor, faithfulness, etc. Current reinforcement learning from human feedback (RLHF) mainly focuses on a fixed reward learned from average human ratings, which may weaken the adaptability and controllability of varying preferences. However, creating personalized LLMs requires aligning LLMs with individual human preferences, which is non-trivial due to the scarce data per user and the diversity of user preferences in multi-objective trade-offs, varying from emphasizing empathy in certain contexts to demanding efficiency and precision in others. Can we train one LLM to produce personalized outputs across different user preferences on the Pareto front? In this paper, we introduce Multi-Objective Control (MOC), which trains a single LLM to directly generate responses in the preference-defined regions of the Pareto front. Our approach introduces multi-objective optimization (MOO) principles into RLHF to train an LLM as a preference-conditioned policy network. We improve the computational efficiency of MOC by applying MOO at the policy level, enabling us to fine-tune a 7B-parameter model on a single A6000 GPU. Extensive experiments demonstrate the advantages of MOC over baselines in three aspects: (i) controllability of LLM outputs w.r.t. user preferences on the trade-off among multiple rewards; (ii) quality and diversity of LLM outputs, measured by the hyper-volume of multiple solutions achieved; and (iii) generalization to unseen preferences. These results highlight MOC's potential for real-world applications requiring scalable and customizable LLMs.

Human perception interprets video dynamics by constructing structured mental representations of entities, actions, and temporal boundaries before engaging in high-level reasoning. In contrast, current Video-LLMs typically rely on unstructured Chain-of-Thought (CoT), where crucial visual cues are obscured by verbose narration. While recent efforts ground reasoning in intermediate visual evidence, they rely on task-specific schemas that fail to generalize across diverse video understanding tasks. To address this, we introduce Structured Event Evidence, a unified, temporally ordered schema designed for general video reasoning. However, post-training a model to extract structured evidence while reasoning introduces a severe multi-objective optimization bottleneck, as candidate rollouts must simultaneously satisfy schema compliance, task accuracy, and reasoning budget. Standard reinforcement learning (RL) algorithms attempt to balance these objectives via static scalarization, enforcing a rigid accuracy-length trade-off across training and obscuring fine-grained reward signals. We resolve this by proposing Group-Relative Advantage Balancing (GRAB), which dynamically computes Pareto-optimal objective weights within each rollout group via a minimum-norm criterion over centered rewards. Operating strictly in reward space, GRAB incurs virtually zero computational overhead (<0.002% relative runtime to GRPO) and eliminates brittle weight tuning. Supported by our new PARSE-60K dataset (60K annotations across 35K videos) and a three-stage progressive curriculum, we train PARSE-4B. Across temporal grounding and video question-answering benchmarks, GRAB generates 13% to 39% fewer tokens while maintaining competitive accuracy with exhaustively hand-tuned static weights -- without requiring hyperparameter weight sweeps.

End-to-end planning has emerged as a dominant paradigm for autonomous driving, where recent models often adopt a scoring-selection framework to choose trajectories from a large set of candidates, with diffusion-based decoding showing strong promise. However, directly selecting from the entire candidate space remains difficult to optimize, and Gaussian perturbations used in diffusion often introduce unrealistic trajectories that complicate the denoising process. In addition, for training these models, reinforcement learning (RL) has shown promise, but existing end-to-end RL approaches typically rely on a single coupled reward without structured signals, limiting optimization effectiveness. To address these challenges, we propose HAD, an end-to-end planning framework with a Hierarchical Diffusion Policy that decomposes planning into a coarse-to-fine process. To improve trajectory generation, we introduce Structure-Preserved Trajectory Expansion, which produces realistic candidates while maintaining kinematic structure. For policy learning, we develop Metric-Decoupled Policy Optimization (MDPO) to enable structured RL optimization across multiple driving objectives. Extensive experiments show that HAD achieves new state-of-the-art performance on both NAVSIM and HUGSIM, outperforming prior arts by a huge margin: +2.3 EPDMS on NAVSIM and +4.9 Route Completion on HUGSIM.

We consider multi-objective reinforcement learning problems where objectives come from an identical family -- such as the class of reachability objectives -- and may appear or disappear at runtime. Our goal is to design adaptive policies that can efficiently adjust their behaviors as the set of active objectives changes. To solve this problem, we propose a modular framework where each objective is supported by a selfish local policy, and coordination is achieved through a novel auction-based mechanism: policies bid for the right to execute their actions, with bids reflecting the urgency of the current state. The highest bidder selects the action, enabling a dynamic and interpretable trade-off among objectives. Going back to the original adaptation problem, when objectives change, the system adapts by simply adding or removing the corresponding policies. Moreover, as objectives arise from the same family, identical copies of a parameterized policy can be deployed, facilitating immediate adaptation at runtime. We show how the selfish local policies can be computed by turning the problem into a general-sum Markov game, where the policies compete against each other to fulfill their own objectives. To succeed, each policy must not only optimize its own objective, but also reason about the presence of other goals and learn to produce calibrated bids that reflect relative priority. Under mild assumptions, we prove the existence of Nash equilibria where dishonest bidding leads to suboptimal outcome, and the most urgent objectives win control automatically. In our implementation, the policies are trained concurrently using proximal policy optimization (PPO). We evaluate on two Atari games and a gridworld-based path-planning task with dynamic targets. Our method achieves substantially better performance than monolithic policies trained with PPO.