Comparative control theory analysis reveals a fundamental trade-off: transitioning from continuous to discrete rule-based control induces high-frequency Bang-Bang actuation and a stable bimodal limit cycle.
Abstract
In safety-critical sectors such as robotics and automotive engineering, the deployment of Deep Reinforcement Learning (DRL) is often hindered by the black-box nature of deep neural networks. This lack of transparency poses significant challenges for regulatory compliance and human-agent trust. This paper presents an experimental study aimed at making high-performance continuous control DRL systems interpretable. A policy distillation framework is implemented using the classic Inverted Pendulum benchmark. A high-performance Twin Delayed DDPG (TD3) agent serves as an opaque, continuous teacher model, whose policy is distilled into an interpretable student surrogate based on a shallow Decision Tree. By leveraging a custom physics-aware feature and"Noisy Oracle Rollouts"for dataset generation, the distillation process achieves performance equivalent to the expert teacher. Furthermore, comparative control theory analysis reveals a fundamental trade-off: transitioning from continuous to discrete rule-based control induces high-frequency Bang-Bang actuation and a stable bimodal limit cycle. Simulation results indicate that Bounded-Input Bounded-Output (BIBO) stability is maintained while providing both global and local interpretability for safe autonomous systems.
Low-altitude micro downbursts pose a severe threat to aviation safety, yet conventional control approaches and standard deep reinforcement learning (DRL) often fail due to explicit modeling difficulties and sparse reward constraints. To address these challenges, this study proposes an explainable, data-driven framework integrating active-reward proximal policy optimization (AR-PPO). A bilevel optimization architecture driven by meta-gradients is developed to dynamically discover optimal reward functions without human intervention. Furthermore, a policy distillation pipeline utilizing wavelet-multivariate singular spectrum analysis (W-MSSA) and classification and regression trees (CART) is proposed to translate high-frequency continuous neural outputs into discrete, pilot-readable rules. Simulation results on a B737-800 model demonstrate that AR-PPO effectively overcomes the “stall trap” by autonomously learning to trade altitude for airspeed, outperforming static-reward baselines and empirical human pilots in extreme, zero-shot windshear encounters (22.0 m/s downdraft). Ultimately, the proposed framework successfully distills black-box AI strategies into verifiable, physics-informed standard operating procedures (SOPs), providing a highly transparent and robust solution for autonomous windshear escape and future competency-based flight training.
Reinforcement learning (RL) enables the synthesis of control policies directly from data, making it highly appealing for complex cyber-physical systems (CPSs) and robotics. A persistent challenge, however, is ensuring strict, hard safety constraints during the active learning phase. In real-world physical systems, violating mechanical limits can cause irreversible damage, necessitating that exploration remains strictly within safe operational regions. We propose a generalized framework that combines the adaptive, high-performance nature of deep reinforcement learning (DRL) with the formal safety guarantees of model predictive control (MPC). Using a mathematical model of the system dynamics, offline MPC computations define a feasible state-action space, representing all safe combinations of system states and control inputs that guarantee constraint satisfaction. During training and deployment, the RL agent's instantaneous actions are projected onto this globally verified feasible set via a safety filter. We systematically evaluate our generalized approach on a non-linear 1-DoF laboratory testbed, demonstrating successful exploration and stable policy convergence on physical hardware.
George Schafer, Jakob Rehrl, Stefan Huber et al.· 0 citations
Deep reinforcement learning (DRL) agents achieve strong performance in complex environments, yet their decision-making processes remain difficult to interpret. We introduce SPOT (Sampling Policy Observation Tree), a novel model-agnostic, sampling-based framework for interpreting DRL policies. Given access to the policy and an environment simulator, SPOT constructs an interpretable finite-horizon tree by sampling actions and recursively simulating the resulting successor states. The tree provides an empirical representation of the policy's action preferences and their possible downstream evolution. We provide formal guarantees establishing SPOT's asymptotic recovery of the policy's unique most probable action and characterizing its disagreement behavior under high-entropy policies. We demonstrate SPOT in the SUMO-RL traffic-signal control domain. The case study illustrates how its tree-based representation can be used to inspect policy preferences, compare alternative future trajectories, and reveal downstream behaviors that are not visible through single-timestep feature-attribution methods.
Deep reinforcement learning (DRL) offers powerful control for industrial cyber-physical systems (ICPSs), but its"black-box"exploration risks violating strict hardware safety limits. Typically, these constraints are managed through complex reward shaping. In this work-in-progress paper, we embed a differentiable physics model directly into the proximal policy optimization (PPO) actor loss function. By simulating short-horizon future trajectories during training, the policy is penalized for anticipated safety violations independent of the task-reward signal. Evaluated on a simulated 1-degree-of-freedom helicopter testbed with strict pitch constraints, our physics-informed soft regularizations substantially reduce constraint violations while maintaining reliable target tracking.
George Schafer, Jakob Rehrl, Stefan Huber· 0 citations
Reinforcement learning (RL) with verifiable rewards constructs trajectory-level advantage estimates, yet it often fails to credit the few pivotal decisions that determine outcomes in long-horizon, multi-turn agentic tasks. Recent work introduces privileged self-distillation for credit assignment, providing denser supervision, but it remains unclear how such local signals should represent sequential credit. We propose AgentOPSD, a critic-free, recursive method for turn-level credit assignment in agentic reinforcement learning. AgentOPSD aggregates token-level teacher-student log-probability gaps into turn-level evidence and recursively updates a Bayesian belief state in log-odds space. This yields a principled reweighting scheme that converts sparse outcome supervision into turn-level credit signals and identifies pivotal turns through the marginal belief revision between consecutive states. The method is fully compatible with standard policy optimization and requires neither an additional critic nor extra rollouts. We evaluate AgentOPSD on ALFWorld, WebShop, and Search-QA using Qwen2.5 models at two scales (3B and 7B). AgentOPSD outperforms GRPO and strong self-distillation baselines, achieving 89.1% success on ALFWorld with Qwen2.5-7B. Ablation studies attribute the gains to turn-level aggregation and history-dependent recursive belief updates.
Zi-Han Wang, Zhengxi Lu, Zhiyuan Yao et al.· 0 citations
Recent advances in post-training Large Language Models (LLMs) increasingly rely on Reinforcement Learning with Verifiable Rewards (RLVR) or On-Policy Self-Distillation (OPSD). While OPSD provides dense, logit-level supervision, it inherently suffers from exposure bias due to the privileged information of the self-teacher. In multi-turn agentic settings, this leads to reasoning route convergence and the loss of clear optimization directions. To tackle these challenges, we introduce Contrastive Reinforced Policy Optimization (CRPO), which reformulates agentic OPSD from a contrastive learning perspective. By leveraging predictive entropy to distinguish between positive positions (reflective exploration) and negative positions (exposure bias), CRPO conducts group-wise contrast to preserve reliable, fine-grained optimization signals. Extensive evaluations across 13 challenging reasoning and deep-search benchmarks demonstrate that CRPO consistently outperforms existing reinforcement learning and self-distillation baselines, significantly enhancing training stability and generalization in long-horizon interactions.
Xingjian Wu, Junlin Liu, Xingchen Liu et al.· 0 citations