arXiv subjects

Hari Prasad

Publications and source records attributed to Hari Prasad.

5 recordsLinked to original sources

arXiv2026

A Transdiagnostic Space of Disorder Like Phenotypes in Reinforcement Learning Agents

Modelling psychological disorders in artificial agents offers a testbed for computational psychiatry and a lens on affective-control failure modes. Prior work induces one or two disorders by hand-tuned reward shaping, labels the behaviour post hoc, and reports single runs. We recast disorder modelling as dose-controllable manipulation of cognitive appraisal signals in an appraisal-guided PPO agent, expressing seven disorders (anxiety, mania, obsessive-compulsive checking, depression, impulsivity, addiction, and post-traumatic stress) each as a single knob grounded in a computational psychiatry account, with each symptom measured by a preregistered assay. Across more than a thousand runs (10 seeds, four controls, 95% confidence intervals) every disorder shows a graded, monotone dose-response that no control reproduces. Beyond these induced effects, three findings emerge that were not written into the reward: disorders self-organise into a two-dimensional affective space in which mania mirrors anxiety; removing a knob remits reward-distortion disorders (mania, checking, addiction) but not avoidance disorders (anxiety, PTSD), which recover under a graded exposure curriculum; and two simultaneous knobs interact nonadditively, yielding testable comorbidity predictions. The depression and addiction knobs further reproduce their double dissociation in a 3D pixel environment (MiniWorld) with a standard convolutional agent and no appraisal critic, showing the framework generalises beyond grid worlds.

cs.LG↗

arXiv2026

The Joint Effect of Quantization and Sampling Temperature on LLM Safety Alignment: A Factorial Analysis

Modern LLM deployments often combine quantization with higher sampling temperatures to reduce cost, latency, or repetition, yet safety evaluations usually treat these as fixed implementation details. We test whether models that are safe at FP16 with greedy decoding remain safe after quantization and stochastic sampling, or whether the two factors amplify each other. We evaluate 8 instruction-tuned models from five families across 3 precisions and 6 temperatures, covering 144 configurations on 7 harmfulness benchmarks and generating about 2.0 million responses, which are scored by a six-judge safety ensemble. Contrary to concerns that low-bit deployment erodes alignment, we find that standard quantization is approximately safety-neutral: for 7 of 8 models, AWQ INT4 keeps attack success within about 1.6 percentage points of FP16 or lowers it, with clear degradation only for SmolLM3-3B (34.5% to 44.1%). However, the larger risk comes from sampling: higher temperatures sharply increase decision instability, with DFR reaching 41.9% at T = 1.0, even when average ASR changes only modestly. The two factors do not compound: our Compound Degradation Index remains sub-additive (-0.071 to +0.018), indicating that quantization partially offsets rather than amplifies temperature-induced degradation. Finally, a per-benchmark breakdown shows that single-benchmark evaluation badly understates risk: several models scoring 0% on AdvBench exceed 80% on ManyHarm. Standard INT4/INT8 quantization can therefore be reasonable for well-aligned models, but safety claims should report multi-sample stability across multiple benchmarks rather than rely on a single benchmark at greedy decoding.

cs.LG↗

arXiv2026

Auditing the Risk Claims of Distributional Reinforcement Learning

Distributional reinforcement learning agents learn full return distributions that are increasingly read at face value: for interpretability, risk-sensitive control, and safety monitoring. We ask a question theory anticipates but that has not been measured directly: are the risk claims of a trained distributional agent true? Our audit combines a decision-relevant screening metric (the excess Wasserstein gap between the top two actions, which equals the mass by which first-order stochastic dominance is violated), ground truth from snapshot-restart Monte Carlo, and a statistical harness (permutation nulls, bootstrap refutation, FDR control) without which the audit itself manufactures false conclusions. Across QR-DQN, C51, and IQN on MinAtar (33 runs), 40-95% of the strongest claimed risk trade-offs are refuted at 95% confidence, the placement of the strongest claims is statistically indistinguishable from truth-blind, and essentially no claim is confirmable: for these agents, the learned "risk" reflects a training artifact rather than environment stochasticity. The artifact is structural (fully formed early in training, uncorrelated with final score, idiosyncratic to each seed) and appears unchanged at full-Atari scale, with every top Breakout claim of a pretrained near-state-of-the-art QR-DQN refuted. Positive controls of known magnitude confirm 96-100% of real claims (correlation 0.89-0.92): the reading measures the agents, not the audit. Acting on the heads' CVaR advice at their most-flagged states ranges from beneficial to significantly worse than chance. Neither training for risk nor ensembling removes the artifact, and recalibration passes the audit only by nullifying the claims: the head is uninformative, not merely miscalibrated. We release the toolkit and document two silent pitfalls that produced convincing but wrong audits of our own.

cs.AI↗

arXiv2024

Appraisal-Guided Proximal Policy Optimization: Modeling Psychological Disorders in Dynamic Grid World

The integration of artificial intelligence across multiple domains has emphasized the importance of replicating human-like cognitive processes in AI. By incorporating emotional intelligence into AI agents, their emotional stability can be evaluated to enhance their resilience and dependability in critical decision-making tasks. In this work, we develop a methodology for modeling psychological disorders using Reinforcement Learning (RL) agents. We utilized Appraisal theory to train RL agents in a dynamic grid world environment with an Appraisal-Guided Proximal Policy Optimization (AG-PPO) algorithm. Additionally, we investigated numerous reward-shaping strategies to simulate psychological disorders and regulate the behavior of the agents. A comparison of various configurations of the modified PPO algorithm identified variants that simulate Anxiety disorder and Obsessive-Compulsive Disorder (OCD)-like behavior in agents. Furthermore, we compared standard PPO with AG-PPO and its configurations, highlighting the performance improvement in terms of generalization capabilities. Finally, we conducted an analysis of the agents' behavioral patterns in complex test environments to evaluate the associated symptoms corresponding to the psychological disorders. Overall, our work showcases the benefits of the appraisal-guided PPO algorithm over the standard PPO algorithm and the potential to simulate psychological disorders in a controlled artificial environment and evaluate them on RL agents.

cs.AI↗

arXiv2022

Manage risks in complex engagements by leveraging organization-wide knowledge using Machine Learning

One of the ways for organizations to continuously get better at executing projects is to learn from their past experience. In large organizations, the different accounts and business units often work in silos and tapping the rich knowledge base across the organization is easier said than done. With easy access to the collective experience spread across the organization, project teams and business leaders can proactively anticipate and manage risks in new engagements. Early discovery and timely management of risks is key to success in the complex engagements of today. In this paper, the authors describe a Machine Learning based solution deployed with MLOps principles to solve this problem in an efficient manner.

cs.LG↗