Robot crowd navigation requires safe and efficient decision-making under dense, dynamic, and multimodal human--robot interactions. Existing reinforcement-learning methods typically output a single reactive action at each timestep, which limits their ability to represent diverse short-term avoidance strategies. We propose Planning Diffusion Policy Optimization (PDPO), an offline-to-online reinforcement-learning framework that uses a diffusion policy to generate short-horizon action chunks for crowd navigation. PDPO is first pretrained on collision-avoidance demonstrations and then fine-tuned online with PPO by treating the denoising process as an internal decision process. During execution, the policy generates a five-step action chunk and applies it in a receding-horizon manner. Furthermore, we observe an evaluation artifact in common crowd-navigation benchmarks: without explicit boundary constraints, learned agents may leave the valid domain and bypass dense crowds. To address this, we introduce a setting in which boundary violations are treated as collisions. Experiments show that PDPO obtains an improved success rate over strong baselines, and ablations demonstrate that action chunks are especially important for the modified bounded benchmark.
Dynamic spectrum access must coordinate secondary users under bursty primary-user activity while preserving packet reliability and delay. We present TACAN, a centralized policy that represents each channel as a token containing occupancy history and automatic-modulation-classification entropy; a context token supplies queue class, delay and user identity. A Transformer encoder is warm-started from an occupancy-greedy policy and refined with proximal policy optimization. The frozen policies were trained to maintain a channel assignment in every slot, including when queues were empty. We therefore replay them on held-out trajectories and distinguish standby assignment success from packet-present access and packet delivery. In a 20-channel network with 60 primary devices and 4 secondary users, TACAN achieves 92.53% +/- 0.47 packet-present access success, compared with 89.94% for Greedy and 83.53% for PPO+MLP. Its paired gain over Greedy is 2.59 points (parametric 95% CI 1.89-3.29), with wins in all five seeds; the exact two-sided sign-test value is 0.0625. The gain rises from 0.57 points at normal primary-user load to 7.67 points at extreme load. TACAN also reduces mean delivery delay from 1.208 to 1.123 slots and the conditional user-reliability gap from 9.69 to 3.15 points. Delivered packets per SU-slot remain arrival-limited (30.12% versus 30.11%), so no packet-throughput gain is claimed.
Credit assignment in large-language-model reinforcement learning (LLM RL) can be separated into three objects: evidence about success, a transport operator that converts this evidence into token-level advantages, and an update geometry that turns advantages into policy changes. Recent work has greatly improved evidence, sampling, and update geometry, but the transport operator is usually architecture-agnostic. Fixed-discount GAE applies a stationary geometric kernel along token time; group-relative methods broadcast an outcome statistic across an entire response. Neither operator represents the trajectory-specific computation used by the Transformer policy itself. We introduce computation-conditioned credit transport (CCT), a general framework in which a detached statistic of the behavior policy's internal computation parameterizes the causal kernel that transports downstream value through a rollout. Our concrete algorithm, CompPO, maps native attention concentration to a bounded per-token retention gate, uses the gate in both the one-step bootstrap and a path-dependent generalized-advantage trace (Comp-GAE), and co-designs a transport-aligned critic (TAC) that reuses the actor's hidden states and routing information without a second same-scale Transformer. The task reward and clipped PPO policy objective remain unchanged; a constant gate recovers fixed-coefficient GAE. Across five Qwen3-4B seeds, CompPO reaches 61.4% final held-out accuracy (95% CI [60.8,62.0]) versus 53.8% [52.9,54.7] for tuned GRPO. Neither Comp-GAE with a standard critic (55.2%) nor TAC with a fixed gate (56.4%) matches the full model (interaction +2.4 [1.9,2.9]). Shuffle and position controls confirm trajectory-specific alignment; CompPO is stable in 10/12 PPO-grid runs versus 3/12. Frozen evaluation improves over GRPO by 4.3 and 3.9 greedy pass@1 macro points on Qwen3-4B and Llama-3.1-8B-Instruct.
This paper presents an event-driven learning and benchmarking framework for the Dynamic Multi-Depot Vehicle Routing Problem with progressively revealed requests and evolving vehicle states. Masked MLP and Transformer policies are trained through behavior cloning and proximal policy optimization. Deterministic feasibility masking prevents invalid vehicle--request assignments, while fixed-prefix/flexible-suffix route commitments protect completed, active, and near-term decisions and separately measure vehicle reassignment and resequencing. The learned policies are compared with dynamic insertion heuristics and time-limited rolling-horizon optimization. In a 20-scenario policy benchmark, all methods completed every request without invalid actions, but nearest feasible achieved the lowest mean objective and outperformed the learned policies in routing quality, waiting time, stability, makespan, and runtime. Across five independent training runs, PPO had little average effect on the MLP and improved the Transformer on average, although with greater seed variability. Under the common protocol, nearest feasible achieved the lowest combined objective and route disruption, whereas rolling horizon achieved the lowest waiting times and makespan at substantially higher computational cost. The learned policies retained millisecond-level decisions and transferred to instances with up to 80 requests without retraining, but did not outperform the strongest heuristic. No single method was best across routing efficiency, service responsiveness, stability, and online computation.
Faizan Ahmed, Aniket Dixit, James Bruseycs.LG cs.AI
On--off cycling is the main cause of compressor wear in residential heat pumps, yet reinforcement learning (RL) controllers for buildings typically optimise only energy cost and thermal comfort, ignoring how much the learned policy cycles. We add a levelised compressor-wear term to the control reward and study how the resulting behaviour depends on the RL algorithm. Training Soft Actor---Critic (SAC) and Proximal Policy Optimisation (PPO) on an identical Markov decision process for the BOPTEST bestest hydronic heat pump case, we find that SAC learns a continuous modulation policy that keeps the compressor permanently engaged---the operating principle of an inverter-driven heat pump---achieving zero start-ups per day, whereas PPO collapses to bang-bang control that cycles more than the baseline. On the BOPTEST emulator the SAC policy cuts thermal discomfort by up to 90.7% for an 11.5% cost increase, while eliminating all baseline cycling.
Preference-based reinforcement learning (PbRL) for general stochastic MDPs often requires training a reward model. Existing reward-model-free methods are either restricted to bandits or deterministic MDPs, such as DPO or P3O, or use zeroth-order, gradient-free optimization, which in general exhibits a slower convergence rate than gradient-based algorithms. Furthermore, existing reward-model-free preference-based RL algorithms almost exclusively use trajectory-level feedback, which can require significant effort from a human evaluator when trajectories are long. On the other hand, segments are much shorter, so they are easier to compare and evaluate. In this paper, we introduce a novel reward-model-free, critic-free, and gradient-based PbRL algorithm compatible with segment preferences named Segment Pairwise Proximal Policy Optimization (SP3O). SP3O utilizes segment-level preference feedback to construct an accurate policy value difference estimator via off-policy importance sampling, and then uses the estimator to compute the policy gradient via a PPO-type loss function. We provide a theoretical basis for the algorithm and analyze the tradeoff in choosing the segment length. We also evaluate it experimentally against other PbRL/RLHF algorithms in robotic control and LLM finetuning settings to show its improved performance, especially in long-horizon tasks.
Proximal Policy Optimization (PPO) for large language models typically trains its critic by mean-squared-error (MSE) regression on scalar value targets. Although scalar MSE is statistically valid for estimating the conditional expected return, sparse binary rewards in reinforcement learning with verifiable rewards (RLVR) make critic optimization and calibration especially consequential: small value errors directly distort the scalar advantages used by PPO. We study whether a classification-based training objective can improve this critic signal. HL-Gauss PPO replaces the scalar MSE head with a categorical predictor over a discretized value support, trained by cross-entropy against smoothed HL-Gauss targets. Its output is decoded to a scalar expectation for standard GAE and PPO; the actor update is therefore unchanged and is not distributional. Across mathematical reasoning, tool-augmented math, and Search-R1, and on both Qwen2.5 and Qwen3 backbones, HL-Gauss PPO consistently improves over strong PPO and DAPO baselines. Controls with one-hot, two-hot, and Bernoulli two-bin critics show that neither a larger output head nor binary classification alone explains the gains. On a common collection of reasoning prefixes, HL-Gauss improves Brier score and calibration error and yields more symmetric, lower-variance advantages. These results position categorical value learning as an effective optimization surrogate for PPO critics in RLVR.
Tabular data generation supports analysis and decision-making when target-domain data are scarce, yet collecting complete target samples is often costly. A practical but underexplored setting provides only a few target records together with richer source data from a related domain. Existing few-shot tabular generators often either fit sparse target statistics directly, which can overfit incidental patterns, or reuse source-domain generators, which may preserve dependencies that no longer hold in the target domain. To address this problem, we propose LAB-Tab, an LLM-augmented Bayesian network (BN) adaptation framework for source-aware few-shot tabular generation. LAB-Tab first fits a BN from source data and then uses an LLM to propose plausible target-domain BN edges that are absent from the source BN graph. This step converts semantic and weak statistical evidence into explicit structural hypotheses, thereby expanding the editable edge space beyond the source-fitted graph. Because the proposed edges may be noisy and interact with existing dependencies, a PPO policy calibrates edges in the augmented BN through edge-level actions, including keep, weaken, strengthen, flip, and deactivate. The PPO policy is trained with a reward that combines distributional alignment, downstream utility, and preservation of target-relevant dependencies. The adapted BN is then sampled to synthesize target-domain tables. Across six source--target distribution-shift scenarios built from three US Census (ACS) prediction tasks, LAB-Tab achieves the best performance at the 10% target-data budget, leads four of the six individual scenarios, and reduces the macro Overall score by 33.8% relative to the strongest baseline. It also obtains the best macro JSD, WAPE, and UtilityGap while maintaining competitive feature--label preservation.
Dheeraj Poolavaram, Aanchal Rajesh Chugh, Sebastian Dorncs.AI
The online three-dimensional bin packing problem (3D-BPP) is a longstanding challenge in logistics and industrial palletizing. Recent learning-based methods use a learned policy to select among feasible candidate placements. Performance depends on the candidate generator and representation, especially in industrial settings where packings must be space-efficient, stable, compact, and balanced. However, prior work has mainly optimized the policy, while candidate generation and representation remain largely geometry-driven. We address this gap with OPAL, an operationally guided placement-aware learning framework for industrial online 3D-BPP which combines an Operationally Guided Empty-Maximal-Space generator (OG-EMS), an operational representation for each candidate placement, and a masked ranking policy trained with proximal policy optimization. OG-EMS evaluates multiple anchors within each free-space region and prioritizes low, well-supported, compact, and spatially diverse placements. An xLSTM-based Placement Encoder models dependencies among geometric and operational candidate attributes, while a lightweight recurrent core combines the resulting embeddings with the current item and pallet state to rank feasible actions. On the BED-BPP benchmark, OPAL achieves a mean space utilization of 0.49, with improvements of 15.1% from operationally guided candidate generation and 6.3% from learned ranking, while maintaining robust inference-time performance.
The alignment of Small Language Models (SLMs) in the 70--500M parameter range using reinforcement learning is often considered unstable, though the underlying failure mechanisms have not been systematically investigated. In the State-of-the-Art (SOTA) research, fifteen (model, corpus) configurations were trained using Proximal Policy Optimization (PPO). The experiments included Pythia-70M, 160M, 410M and SmolLM2-135M, 360M on the TinyStories, CNN/DailyMail, and Wikitext-103 corpora. Three reproducible failure modes were identified in small-scale language models: silent LoRA parameter freezing in standard PEFT/TRL pipelines, numerical overflow in importance ratios when using bfloat16, and catastrophic policy collapse due to reward-model error. These issues were addressed using a merge-and-reinitialize adapter technique, float32 precision during PPO updates, and a three-layer safety mechanism comprising reward whitening, importance-ratio guarding, and weight rollback. In this paper, a capacity-headroom hypothesis is proposed, which states that PPO performance at the SLM scale depends on both a fluent supervised model ($\text{PPL}<20$) and a discriminative reward signal, rather than on the number of model parameters. The proposed system converged stably in all experiments and improved preference win rate over the SFT baseline in configurations with a fluent prior and an informative reward signal. Furthermore, it outperformed instruction-tuned baselines while requiring significantly less training data. All checkpoints, preference datasets, and training scripts are publicly released$^§$.
We present a traffic-signal control interface in which a shared graph neural network assigns scores to individual traffic movements. Each junction converts these scores into its own variable-sized set of legal signal phases using a deterministic incidence matrix. Directed corridor nodes provide traffic context, while movement nodes represent controlled input-to-output paths through junctions. Typed mean aggregation produces one scalar per movement; phase definitions and signal timing remain outside the learned network. This makes graph size and junction-specific action count independent of the learned parameter shapes. PPO experiments evaluate the interface on unseen synthetic grid geometries, altered signal coverage, and five heterogeneous city graphs. The policies retained performance across unseen geometries within the synthetic grid family, while changes in signal coverage exposed sensitivity to a signal-coverage distribution shift. A single trained city-policy instance executed across all five city graphs, with heterogeneous outcomes. These results provide feasibility evidence rather than a general estimate of transfer to arbitrary road networks.
This paper presents our system for Task 3 of the CLEF 2026 FinMMEval Lab, which requires daily long, flat, or short trading decisions for Bitcoin (BTC) and Tesla (TSLA) using news and historical market data. We formulate the problem as a discrete-action Markov Decision Process and compare four deep reinforcement learning algorithms: Policy Gradient (PG), Proximal Policy Optimization (PPO), Deep Q-Learning (DQL), and Deep Deterministic Policy Gradient (DDPG). The agents use technical indicators, cyclical calendar encodings, and daily news sentiment scores produced by LLaMA 3.2 1B. To reduce overfitting and align training with the objective of outperforming buy-and-hold, we introduce an alpha reward based on excess market return and randomize episode start dates. Hyperparameters are optimized with Ray Tune over 180 trials per algorithm-asset pair, with early stopping and model selection based on validation Sharpe ratio. On the CLEF Task 3 test set, DDPG achieves the strongest overall performance. DQL was selected a priori for the live endpoint because it obtained the highest validation Sharpe ratio, with selection performed without access to the test period. For TSLA, DDPG and DQL achieve cumulative returns of 54.96% and 52.62%, respectively, compared with 16.45% for buy-and-hold. For BTC, DDPG achieves a positive return of 1.58% while buy-and-hold declines by -34.27%. The results also reveal a substantial validation-to-test generalization gap, highlighting the difficulty of transferring policies selected in bull-market conditions to a bear-market regime.
Reinforcement learning holds significant potential for training large language models (LLMs) to handle multi-turn interactive tasks. However, in long-horizon, multi-turn tasks characterized by sparse outcome rewards, directly training with outcome rewards often results in slow convergence due to the sparsity of signals and the lack of fine-grained feedback. Furthermore, the model may fail to learn successful trajectories that are not sampled during training, thereby limiting its performance. Conversely, while employing customized dense process rewards provides richer signals and accelerates convergence, these surrogate rewards may exhibit potential misalignment with the ground-truth outcome rewards. This inconsistency can bias the training direction and ultimately degrade the model's final performance. In this work, we propose Reward-Swap Policy Optimization (RSPO), a method designed to leverage the rich information from dense process rewards to facilitate training with outcome rewards. By utilizing a reward-swap mechanism, RSPO ensures the diversity of sampled trajectories while guaranteeing consistency between the optimization objective and the true outcome rewards, thereby elevating the performance ceiling of the model. We conduct extensive experiments on two challenging agent benchmarks, WebShop and ALFWorld. By applying our method to various reinforcement learning algorithms, including GRPO, PPO, and GiGPO, we demonstrate that RSPO achieves consistent performance improvements across different baselines and benchmarks.
Ranjit Raut, Aarav Subedi, Sagun Rai +2cs.AI cs.GT
Baghchal is a two-player asymmetric board game with Nepali origins where four tigers are to capture goats and twenty goats desire to keep tigers in immobility. Although Baghchal has a complex structure which is strategic, has perfect information structure, and has cultural meaning, it has not been adequately covered in deep reinforcement learning (RL) literature. This paper gives a systematic exploration of four deep RL solutions Deep Q-Network (DQN), REINFORCE, Proximal Policy Optimization (PPO) and MuZero that are trained on one side of the asymmetric gameplay of Baghchal and then evaluated on the other side. The algorithms are rated based on win rate, draw rate, average captures, training convergence and computational cost. It is experimentally found that MuZero generates the best performance in both tasks, achieving 86 percent win over these Tiger and 62 percent win over these Goat and the ability to do so is due to the model-based planning machine through the Monte Carlo Tree Search. PPO is the most realistic algorithm and is provided to be competitive over both asymmetric tasks with significantly reduced computational costs compared to MuZero. Emergent strategic behavior analysis shows that model-based strategies are optimal over long-horizon planning, whereas value-based counterparts like DQN are more biased up towards the Tiger role owing to the more substantial reward signal.
Actor-critic methods depend on learned critics, but critic quality is often evaluated only indirectly through return, temporal-difference error, or value loss. Critic complexity is introduced as an additional diagnostic and intervention dimension for actor-critic reinforcement learning. The analysis uses spectral effective-rank entropy, a rank-like summary of the singular-value distributions of critic weight matrices, to assess critic model complexity. Across TD3 and PPO experiments, critic complexity is tracked together with return and Monte Carlo value-estimation bias. The results show that critic complexity is measurable throughout training and is systematically associated with training behavior, while also making clear that the relationship is heterogeneous across algorithms, tasks, and hyperparameters. A direct complexity-control intervention is then evaluated by adding a spectral-entropy penalty to the critic loss. This intervention reliably changes the targeted spectral quantity, demonstrating that critic complexity can be controlled rather than only observed. Return effects are treated as task-dependent evidence rather than as a general performance claim, because overall complexity-control results vary.
Rui Wang, Linchao Zhang, Qiang Liu +1eess.SP cs.LG cs.NI
Outer-loop link adaptation (OLLA) is widely deployed in 5G NR to track channel variations, yet its reliance on first-order, single-bit feedback degrades performance significantly under high-mobility and fast-varying channels. This paper presents LOLLA (Learned Outer-Loop Link Adaptation), a deep reinforcement learning framework that replaces the conventional OLLA staircase with a learned, continuous SINR offset conditioned on rich PHY/MAC telemetry inaccessible to OLLA. The offset modulates the SINR-to-MCS lookup table, preserving 3GPP-compliant MCS selection and provably subsuming the conventional OLLA update rule. A Proximal Policy Optimization (PPO) policy trained under a Lagrangian block error rate (BLER) constraint automatically enforces tunable reliability targets from 1% to 15% without manual penalty calibration. The framework is realized as the first closed-loop AI-native control dApp on a GPU-accelerated 5G NR stack, achieving end-to-end control latencies under 500 microseconds. Evaluations under 3GPP TDL channel models demonstrate 15% to 92% throughput gains over OLLA across Doppler frequencies up to 400 Hz, while attaining a Pareto frontier that strictly dominates OLLA across all evaluated reliability targets. The learned policy generalizes to unseen channel models and scales to eight concurrent UEs under shared-resource scheduling. In the uplink formulation, the gNB directly observes decoding outcomes, enabling simulation-to-deployment parity.
Logic synthesis optimization poses significant challenges due to exponentially growing search spaces, sparse reward signals, and diverse logic structures. Traditional expert-designed flows lack adaptability, while reinforcement learning (RL) methods often suffer from low sample efficiency and limited interpretability. We introduce SKILL, a Self-correcting Knowledge-guided Iterative Large Language Model Agent that unifies multi-agent LLM reasoning and RL-based environment interaction for automated synthesis optimization. SKILL coordinates three specialized LLMs: GPT-4o for strategic planning, Claude Sonnet 4 for detailed reasoning, and Gemini 2.5 Pro for efficient analysis with a PPO-based RL agent that learns actionable policies through direct interaction with synthesis tools. A novel self-correcting module monitors environment feedback (PDA metrics), detects suboptimal behaviors, and invokes LLM-guided recovery strategies. Evaluations on IWLS, OpenCores, and EPFL benchmarks show SKILL achieves a 12.4 % PDA improvement over expert flows and 86.3% success rate on logic systems up to 500K gates.
David Eje, Tanmay Sharma, Khush Patel +2cs.LG cs.AI
Detecting anomalies in large-scale system logs is critical for the reliability and security of modern computing infrastructure. We present LogNEO, a log anomaly detector built on EleutherAI's GPT-Neo (1.3B parameters) and fine-tuned with a novel partial-credit, exponentially decaying position-aware reward scheme combined with cross-entropy regularisation via Proximal Policy Optimisation (PPO). The position-aware reward explicitly models prediction difficulty: early positions receive higher rewards for correct predictions, while later positions incur stronger penalties for errors. LogNEO attains F1-scores of 0.927, 0.913, and 0.984 on the HDFS, BGL, and Thunderbird benchmarks, improving recall by up to 6 percentage points over the prior state-of-the-art LogGPT while maintaining comparable precision. A production microservice deployment over Apache Kafka, Redis, and TensorRT-accelerated inference demonstrates 45 ms end-to-end latency at 15,000 events per second.
Bingxu Liu, Jiashun Liu, Johan Obando-Ceron +5cs.LG cs.AI
While Proximal Policy Optimization (PPO) demonstrates strong performance in stationary settings, we show that its standard optimization paradigm struggles in continual and non-stationary environments. The failure does not stem from insufficient model capacity or overly restrictive clipping. Instead, PPO performs persistent, directionally inefficient local updates, which indicates a lack of geometry-aware guidance for accumulating meaningful behavioral change and ultimately hindering transitions toward new behavior patterns. Although divergence-based regularization introduces partial geometric awareness, its monotonically increasing penalties implicitly discourage large policy deviations, even when such shifts are necessary for effective adaptation. To address this limitation, we propose Gaussian Trust Region Policy Optimization (GTR), which reshapes the trust region using a Gaussian kernel. The resulting constraint is bounded and non-monotonic, providing strong local stability while progressively relaxing under sustained high-advantage updates. To further improve robustness, we introduce a Mixture Gaussian Anchor that adapts to recent policy trajectories, reducing variance induced by stale references. GTR is architecture-agnostic and achieves strong performance across games, simulated robotic control, open-world exploration, and language model post-training. These results demonstrate that geometry-aware trust-region design can be a promising direction for robust reinforcement learning in complex non-stationary environments. Our code is available at https://anonymous.4open.science/r/GTR_demo/README.md.
Deokgyu Yoon, Hyungkyu Kang, Joongkyu Lee +4cs.LG cs.AI
Reinforcement learning with verifiable rewards (RLVR) plays a pivotal role in improving the reasoning ability of large language models. However, widely used PPO surrogate objectives are fundamentally local, as they rely on a local approximation of the exact policy gradient objective. While this approximation improves stability by reducing the variance induced by importance sampling, it also introduces structural bias into the surrogate objective, which must be controlled through trust region mechanisms. In this work, we introduce the $N$-step forward trace, which augments the PPO surrogate objective using the cumulative likelihood ratio of the next $N-1$ tokens. Building on this idea, we propose $N$-Step Forward-Trace Policy Optimization (NFPO), a practical RLVR algorithm that integrates the $N$-step forward trace into the masked policy gradient framework. NFPO provides a continuous bridge between the PPO surrogate objective and the exact policy gradient objective, offering a principled mechanism for controlling the bias-variance trade-off. Our theoretical analysis shows that, with an appropriate choice of $N$, the proposed objective yields a tighter policy-improvement bound than the standard PPO surrogate. Experiments on comprehensive reasoning benchmarks demonstrate that NFPO consistently improves performance, supporting our theoretical findings.
System Neural Diversity (SND) measures behavioral heterogeneity in multi-agent reinforcement learning by averaging pairwise distances over all $\binom{n}{2}$ agent pairs, making each call quadratic in team size. We introduce Graph-SND, which replaces this complete-graph average with a weighted average over the edges of an arbitrary graph $G$. Three regimes follow: $G=K_n$ recovers SND exactly; a fixed sparse $G$ defines a localized diversity measure at $O(|E|)$ cost; and random edge samples yield an unbiased Horvitz-Thompson estimator and a normalized sample mean with $O(1/\sqrt{m})$ concentration in the sampled edge count $m$. For fixed sparse graphs we prove forwarding-index distortion bounds for expanders and a spectral refinement under low-rank distance structure; for random $d$-regular graphs we prove an unconditional probabilistic $\widetilde{\mathcal{O}}(D_{\max}/\sqrt{n})$ bound. On VMAS we verify recovery, unbiasedness, concentration, and wall-clock scaling, with a PettingZoo TVD panel checking non-Gaussian transfer. In a 500-iteration $n=100$ PPO run, Bernoulli-$0.1$ Graph-SND tracks full SND while reducing per-call metric time by about $10\times$, and frozen-policy GPU timing up to $n=500$ follows the predicted $\binom{n}{2}/|E|$ speedup. Random $d$-regular expanders empirically achieve $\mathrm{SND}_{G}^{\mathrm{u}}/\mathrm{SND} \in [0.9987, 1.0013]$ at $Θ(n \log n)$ edges. In DiCo diversity control at $n=50$, Bernoulli-$0.1$ Graph-SND preserves set-point tracking with paired reward differences indistinguishable from zero across nine matched cells while cutting per-call metric cost by ${\sim}9.5\times$. Together, these results show that the SND aggregation bottleneck can be removed without changing the metric's semantics, yielding a drop-in sparse alternative that scales beyond complete-graph SND and supports both passive measurement and closed-loop diversity control.
Proximal Policy Optimization (PPO) dominates deep RL but faces a fundamental dilemma. Its "hard clipping" mechanism discards valuable gradient information from outliers, leading to sample inefficiency. Conversely, removing clipping (as in SPO) exposes optimization to unbounded gradients, causing significant instability and hyperparameter sensitivity. To resolve this, we establish a Unified Trust Region Framework that generalizes existing objectives. Within this framework, we derive Anchored Neighborhood Optimization (ANO) based on a set of design principles. We identify that the failure of standard policy gradients stems from a misapplication of gradient influence on outliers. We propose the Redescending Influence Principle, a paradigm shift from monotonic penalties (SPO) and hard-thresholding (PPO) to dynamic outlier suppression, and prove its necessity for stability in high-variance stochastic optimization. Theoretically, we prove ANO possesses the minimal structural complexity required for robust optimization. Empirically, ANO achieves state-of-the-art performance on MuJoCo benchmarks, significantly outperforming PPO and SPO. Notably, ANO demonstrates superior stability, preventing policy collapse even under aggressive hyperparameters (e.g., learning rates 3x larger than standard) where PPO fails completely.