Active Curriculum Refinement for Reinforcement Learning

In many reinforcement learning (RL) domains, environments are connected by prerequisite relations, such as difficulty-increasing edits or parameter increments, which induce a directed acyclic curriculum graph (DAG). Although this structure is often exploited only implicitly, explicitly modeling it can improve training. We introduce PATH, a curriculum-learning framework that performs active learning over the curriculum graph. PATH first expands coverage by sampling diverse curriculum paths and then reallocates training toward regions that remain unmastered. Experiments across diverse environments show that PATH explicitly leverages the graph structure to achieve strong robustness and generalization.

Dynamic Context Scheduling: Learning Beyond the Static Universe

We study dynamic context scheduling as a training instrument for contextual re- inforcement learning. Rather than treating intra-episode context variation as a deployment reality, we treat it as a controlled shaping mechanism. Thereby, context evolves within each training episode according to a predetermined schedule, expos- ing the policy to a richer and more temporally structured region of the environment parameter space. We introduce DYNAMICCARLENV, a framework that wraps contextual environments with pluggable schedule families, such as sinusoidal off- sets or cosine annealing. Across CartPole, BipedalWalker and VehicleRacing with CARL contextualization, we show that dynamic schedules match or outperform static context baselines in the out-of-distribution (OOD) regimes. Interestingly, for the more complex BipedalWalker and VehicleRacing environments we also achieve higher in-distribution (ID) evaluation performance. Preliminary findings indicate that automatic search for multi-stage curricula can successfully discover schedules that improve generalization, performing comparably to extensive grid search over single-stage schedulers.

Temporal Logic Guided Universal Task Representations for Reinforcement Learning

Task guided agents demonstrate strong performance in a wide range of complex tasks. However, most existing task representation algorithms are tailored to specific contexts and struggle to generalize across diverse scenarios. Moreover, they typically depend on gradient signals from reinforcement learning controllers to update their weights, which can degrade both representation quality and learning efficiency. To overcome these limitations, we propose LOTUS, a temporal logic inspired universal task representation framework that can be seamlessly integrated into any RL algorithm to enhance agent performance across diverse task settings. Specifically, we design a novel task representation architecture capable of modeling relationships and extracting task semantics from LTL formulas. We further introduce a more effective update mechanism that treats the LTL encoder as a policy, thereby improving representation capacity. To enhance stability and robustness, LOTUS leverages the bisimulation metric, which provides theoretical guarantees for LTL representation, including behavioral equivalence, optimality fidelity, and trajectory robustness. Experimental results show that LOTUS outperforms most existing methods in learning efficiency, generalization capability, and representation quality. Specifically, LOTUS accelerates convergence over 20% in single-task scenarios, achieves a 15%-45% higher success rate in unseen manipulation tasks, and improves generalization performance over 25% in complex multi-task environments with increased sub-goal depth or conjunctions. The corresponding code, videos, and appendix are available at: https://lotus-website.github.io/.

One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL

Multi-agent reinforcement learning for human-AI interaction typically relies on a single large language model to simulate user behavior. We show that this approach systematically fails to generalize, and trace the failure to simulator collapse: because the simulator LLM is mode-collapsed, an LLM policy trained against it overfits to narrow strategies that exploit the simulator's dominant mode, and such a policy transfers poorly to unseen simulators and real users. We formalize this collapse theoretically and propose two complementary solutions, one at inference time and one at training time. The inference-time solution, Verbalized Sampling, broadens the simulator's behavior by sampling from a verbalized response distribution, reducing mode collapse. The training-time solution, Co-Training, jointly optimizes the policy against a population of trainable simulators, preventing it from overfitting to any single simulator's mode. We validate both solutions on three multi-turn benchmarks: Persuasion for Good, $τ^2$-bench, and CooperBench. Verbalized Sampling improves held-out success by up to 9% over single-simulator RL, and Co-Training pushes gains further to 14%; the human study shows similar gain on real users. Both solutions preserve the policy diversity that collapses under single-simulator RL. To support further work in this direction, we release SCOPE, an open-source framework for Population Co-Training multi-agent RL. More broadly, our results suggest that the diversity of the training environment, not only the policy, is critical to the generalization of multi-turn RL to real-world deployment.

Curriculum Generation under Structured Parametric Environments for Robust Navigation Policies

Robust navigation policies for autonomous agents must generalize across continuously varying environmental conditions such as turn rates, obstacles, friction, pits, and slopes. Curriculum generation provides a principled mechanism for improving generalization by progressively adapting training environments, but designing such curricula in a sample-efficient and automated manner remains challenging. This paper proposes a reparameterized curriculum generation framework for structured continuous environment parameters using unidirectional gradient-based optimization. To improve robustness in multimodal observation spaces consisting of image-based and scalar inputs, a distribution-shift regularization objective is incorporated to encourage the learning of finer-grained latent representations. The proposed method is evaluated across two continuous-control OpenAI Gym environments: a 2D obstacle-based Car Racing variant and Bipedal Walker variant, where coupled environment parameters jointly influence policy performance. Across five random seeds, our method consistently outperforms vanilla policy training, random parameter sampling, manual curricula, frontier-based methods, Self-Paced Reinforcement Learning (SPRL), Absolute Learning Progress with Gaussian Mixture Models (ALP-GMM), and reverse curriculum learning baselines. Ablation studies further demonstrate the effectiveness of the reparameterized curriculum mechanism across both environments, while highlighting environment-dependent benefits of the auxiliary regularization objective.

IB-RL: Isolated Bilateral Reinforcement Learning for Strategic Dialogue Agents

Reinforcement learning (RL) has achieved strong results in improving large language models (LLMs) on tasks with stationary, verifiable rewards, such as mathematical reasoning and code execution. In these settings, the environment follows fixed rules and does not adapt strategically to the agent. Strategic dialogue differs in this respect: the environment is another agent that adapts to the policy, and success depends on the interaction between the two sides. Despite this interactive nature, current RL approaches typically train a target agent against a fixed counterpart or simulator. We find that this training paradigm encourages the policy to exploit counterpart-specific regularities rather than learn strategies that generalize across counterparts. We call this problem the static-counterpart mismatch, which we quantify directly in our experiments. To address it, we propose Isolated Bilateral Reinforcement Learning (IB-RL), in which the two roles coevolve through joint rollouts while each role optimizes its own reward through fully independent advantages, action masks, and update paths. We evaluate frozen policies against fully independent held-out counterparts in both domains. On Vehicle TeleSales, IB-RL achieves 89.6% Success@1, compared to 84.6% for the best unilateral RL baseline. On Deal-or-NoDeal, it reaches 98.4% agreement against DeepSeek V4 Pro, compared to 86.4% for the best unilateral baseline. These results indicate that jointly training both roles with strict peragent isolation produces policies that generalize more effectively to unseen counterparts.

Geometric Self-Supervised Pre-training for Neural Combinatorial Optimization

Neural Combinatorial Optimization (NCO) techniques have emerged as a highly efficient alternative to traditional exact algorithms for solving routing problems such as the Traveling Salesman Problem (TSP). However, the generalization capabilities of these Reinforcement Learning-based models are severely hindered when scaling to high-dimensional instances. This issue has been mitigated in other domains, like computer vision and natural language processing, by adopting a self-supervised pre-training strategy. Nevertheless, its application to routing graphs, which lack complex topological attributes beyond 2D spatial coordinates, remains a challenge. In this paper, we propose a geometric self-supervised pre-training framework specifically designed to capture spatial invariance and global relative distance distributions. By applying isometric transformations, such as rotations and axial reflections, the model learns robust structural representations prior to the policy optimization phase. Empirical results demonstrate that this strategy consistently outperforms models trained from scratch (baselines), achieving a 7.23\% improvement in tour length for massive zero-shot extrapolation scenarios (TSP1,000). Furthermore, the proposed model exhibits remarkable computational efficiency, delivering speedups of up to two orders of magnitude over the exact solver Concorde at massive scales. The source code and pre-trained models are publicly available at https://github.com/davidaguadocosano/TSP-GeoPretrain.git.

Beyond Entropy: Correctness-Aware Advantage Shaping via Contrastive Policy Optimization

Reinforcement learning with verifiable rewards (RLVR) commonly uses entropy for advantage shaping. However, entropy cannot distinguish useful uncertainty from detrimental confusion, limiting its effectiveness as a correctness signal. We propose Contrastive Policy Optimization (CPO), which uses token-level contrastive disagreement between reference-guided and vanilla generation distributions for correctness-aware advantage shaping. Both theoretical and empirical results show that this disagreement reliably indicates token-level correctness. We further show that On-policy Distillation is a special case of CPO, where the posterior distribution is instantiated by an external teacher model. CPO also resolves the zero-advantage problem. Experiments on in-domain and out-of-domain benchmarks demonstrate that CPO substantially outperforms entropy-based RLVR methods while maintaining strong generalization. Further analysis shows that correct and incorrect responses naturally support exploration and exploitation respectively, and balancing both leads to the best performance.

Entanglement as a Structural Complexity Axis: A PAC-Bayesian View of Generalization in Quantum Policies and Value Functions

Parameterized quantum circuits (PQCs) are increasingly used as policies and value functions in quantum reinforcement learning, yet it remains unclear when and why quantum policies generalize. We give a PAC-Bayesian account in which generalization is governed not by the raw number of circuit parameters, but by the effective dimension of the Fisher geometry induced by the circuit. This quantity is inflated by entanglement, making entangling connectivity an independent axis of complexity.In controlled experiments that fix the number of trainable rotations and vary only entanglement, we find that circuits with larger Fisher effective dimension exhibit larger train-test gaps, while parameter count is a weak predictor. The resulting bound acts primarily as a ranking certificate: it correctly orders circuits with identical parameter count, which parameter-counting bounds cannot do. We validate this mechanism across supervised classification, quantum contextual bandits, and value-function generalization, where entangled circuits consistently generalize worse than non-entangled circuits of equal parameter count, with gaps shrinking as sample size increases.Our strongest evidence comes from low-variance decision models, including single-observable classifiers, value heads, and one-step policies. In end-to-end multi-step policy learning, entanglement effects remain statistically significant but high return variance leaves the full ordering only partially resolved. Partial-correlation analysis shows that Fisher effective dimension screens off entangling pattern, and controls for training accuracy, readout, and optimizer rule out major optimization confounders. The effect also persists on an IBM Heron quantum processor under real noise. Overall, our results reframe quantum policy design around an entanglement--generalization trade-off rather than expressivity alone.

Generalization in offline RL: The structure is more important than the amount of pessimism

While pessimism counteracts overestimation bias in offline reinforcement learning (RL), being overly conservative has been associated with hindering certain forms of generalization. However, in this paper we demonstrate that being overly pessimistic does not inherently prevent optimal generalization in contextual MDPs (CMDPs). Instead, we argue successful generalization depends not on the amount of pessimism, but whether the pessimistic structure respects the underlying symmetries of the optimal solution. We prove that a mildly pessimistic, non-symmetric value function can generalize worse than an overly pessimistic, symmetric one. In offline RL, the structure of the pessimism is determined by the structure of the dataset coverage. As such, enforcing a symmetric value function can be non-trivial, and might require techniques such as data augmentation (DA). Inspired by our theoretical results, we argue that DA can best be applied through a consistency loss during policy extraction, rather than the common practice of (regular) offline training on an augmented dataset. This is empirically validated using IQL and CQL on a rotationally symmetric reacher environment.

Task-Relevant Representation Decoupling for Visual Reinforcement Learning Generalization

Visual Reinforcement Learning (VRL) has achieved considerable success in solving control tasks. However, generalizing learned policies to new environments remains a major challenge, as agents often overfit to task-irrelevant features in the training environment. To solve this problem, we introduce the concept of decoupling observations into task-relevant and task-irrelevant representations. Building on this idea, we propose a self-supervised Task-Relevant Representation Decoupling (T2RD) algorithm for VRL. This algorithm consists of three components: task-relevant representation consistency, cross-reconstruction, and cross-dynamic prediction. The first two components achieve the decoupling of content and style features, but the resulting content representations are not necessarily task-relevant. To further refine task-relevant features from content representations, we design the third component that introduces dynamic prediction. T2RD achieves State-Of-The-Art (SOTA) generalization performance and sample efficiency in the DeepMind Control Suite and Robotic Manipulation tasks.

Learning Generalizable Skill Policy with Data-Efficient Unsupervised RL

Unsupervised Reinforcement Learning (URL) aims to pre-train scalable, skill-conditioned policies without extrinsic rewards, serving as a foundation for downstream control tasks. Despite recent progress, we argue that current off-policy URL methods are limited by two critical, overlooked bottlenecks: (1) non-stationary skill semantics and (2) brittle generalization. To address these challenges, we propose GenDa (Generalizable Data-efficient Agent), a unified framework for robust unsupervised reinforcement learning. First, we introduce a skill relabeling mechanism to mitigate non-stationarity and significantly improve data efficiency for pre-training. Second, we propose a Complementary Information Bottleneck (CIB), encouraging the learned skill policy to focus on ego-centric features and become robust to distribution shifts for downstream tasks. Through various experiments, we demonstrate that GenDa significantly enhances the scalability of URL with superior generalizability and data efficiency. Our code and videos are available at https://ihatebroccoli.github.io/official-GenDa.

Safe and Generalizable Hierarchical Multi-Agent RL via Constraint Manifold Control

Multi-agent systems are widely used in safety-critical applications that require coordinated behavior under strict safety constraints. Existing approaches face a fundamental trade-off: learning-based methods achieve strong empirical performance but lack theoretical safety guarantees, while control-theoretic methods enforce safety but often lead to overly conservative and inefficient behaviors. We propose a hierarchical multi-agent reinforcement learning framework that enforces hard safety constraints under mild assumptions at low level via a constraint manifold, while enabling effective coordination through high-level policy learning. Our approach provides theoretical safety guarantees in the multi-agent setting and yields stationary learning dynamics, thereby enabling stable and efficient training. Empirically, our method achieves competitive performance while maintaining nearly perfect safety rates, and generalizes effectively to varying numbers of agents and obstacles.

A Unified Causal-Origin Taxonomy of Distributional Shifts in Reinforcement Learning

Reinforcement learning (RL) systems often degrade when operating conditions differ from those previously encountered, reflecting distributional shifts in the underlying data-generating process. Such shifts may occur between training and evaluation, as in In-Distribution (ID) and Out-of-Distribution (OOD) generalization, or within non-stationary settings where environment dynamics evolve over time. However, the formal relationship between these views remains unclear, and existing work mainly focuses on mitigation rather than the causal origin of shift within the agent-environment interaction. This work develops a unified causal-origin taxonomy that characterizes sources of distributional shift in RL and relates ID/OOD generalization to non-stationary settings. We transfer the classical dataset-shift principle from supervised learning to RL by reformulating distributional shift in terms of the generative interaction process. Using a Partially Observable Markov Decision Process (POMDP), we decompose the interaction into structural components, including the state distribution, observation process, policy, reward, and transition dynamics, together with the shifted-time boundary. The proposed taxonomy distinguishes internal, agent-driven, and external, environment-driven, distributional shifts. The shifted-time boundary perspective further characterizes explicit, implicit, and hybrid shifts. This formulation unifies ID/OOD generalization and non-stationarity as structured changes in the underlying process. We also introduce an evaluation framework for measuring shift impact and adaptation through performance degradation and recovery metrics. By grounding distributional shift in the causal-origin structure of RL, this work supports systematic analysis of robustness under distributional shift.

Evolutionary Bilevel Reward Shaping for Generalization in Reinforcement Learning

Reinforcement learning (RL) often suffers from performance degradation when deployed in environments that differ from those encountered during training. Existing techniques such as domain randomization (DR) mitigate this, but require access to diverse training environments and full trajectory observability, assumptions that fail in privacy-preserving or restricted scenarios where only scalar performance metrics are available. We propose Generalization via Evolutionary Reward Shaping (GERS), a bilevel optimization approach to improve generalization on unseen test environments using only scalar feedback from validation environments. At the lower level, an RL agent guided via a reward function shaped by the upper level learns a policy on a limited set of training environments with accessible trajectory data; at the upper level, CMA-ES optimizes the reward shaping parameters to maximize the cumulative unshaped reward on separate validation environments for which trajectory access is unavailable. Results on continuous control tasks indicate that GERS outperforms the standard RL baseline on unseen test environments. GERS performance is comparable to DR, despite DR treating the combined set of training and validation environments of GERS as a single training set that requires trajectory access, whereas GERS cannot access validation trajectories. These results confirm that GERS effectively enhances generalization under restricted data access constraints.

Discovering Lattice Reduction Strategies via Self-Play

The Lenstra-Lenstra-Lovász (LLL) algorithm is a seminal contribution to computer science used for lattice basis reduction, yet its polynomial-time outputs produce bases that are far from optimal as the dimension grows. We show that deep reinforcement learning can discover strictly superior, generalizable reduction strategies by interacting with the primitive action space of LLL. We formulate lattice reduction as a single-player Markov Decision Process (MDP) and train a deep residual network using an AlphaZero-style self-play pipeline augmented with adaptive-horizon MCTS (Monte Carlo Tree Search), which couples multi-step network predictions with an entropy-gated expansion mechanism. The resulting policy, DeltaStar, is trained exclusively on small $8$-dimensional $q$-ary lattices and requires fewer primitive row operations than LLL. Crucially, it generalizes zero-shot to unseen moduli and higher dimensions up to $n=32$ without retraining.

SpecRLBench: A Benchmark for Generalization in Specification-Guided Reinforcement Learning

Specification-guided reinforcement learning (RL) provides a principled framework for encoding complex, temporally extended tasks using formal specifications such as linear temporal logic (LTL). While recent methods have shown promising results, their ability to generalize across unseen specifications and diverse environments remains insufficiently understood. In this work, we introduce SpecRLBench, a benchmark designed to evaluate the generalization capabilities of LTL-based specification-guided RL methods. The benchmark spans multiple difficulty levels across navigation and manipulation domains, incorporating both static and dynamic environments, diverse robot dynamics, and varied observation modalities. Through extensive empirical evaluation, we characterize the strengths and limitations of existing approaches and reveal the challenges that emerge as specification and environment complexity increase. SpecRLBench provides a structured platform for systematic comparison and supports the development of more generalizable specification-guided RL methods. Code is available at https://github.com/BU-DEPEND-Lab/SpecRLBench.