ICML 2025 论文列表

Existing offline hierarchical reinforcement learning methods rely on high-level policy learning to generate subgoal sequences. However, their efficiency degrades as task horizons increase, and they lack effective strategies for stitching useful state transitions across different trajectories. We propose Graph-Assisted Stitching (GAS), a novel framework that formulates subgoal selection as a graph search problem rather than learning an explicit high-level policy. By embedding states into a Temporal Distance Representation (TDR) space, GAS clusters semantically similar states from different trajectories into unified graph nodes, enabling efficient transition stitching. A shortest-path algorithm is then applied to select subgoal sequences within the graph, while a low-level policy learns to reach the subgoals. To improve graph quality, we introduce the Temporal Efficiency (TE) metric, which filters out noisy or inefficient transition states, significantly enhancing task performance. GAS outperforms prior offline HRL methods across locomotion, navigation, and manipulation tasks. Notably, in the most stitching-critical task, it achieves a score of 88.3, dramatically surpassing the previous state-of-the-art score of 1.0. Our source code is available at: https://github.com/qortmdgh4141/GAS.

Leveraging more test-time computation has proven to be an effective way to boost the reasoning capabilities of large language models (LLMs). Among various methods, the verify-and-improve paradigm stands out for enabling dynamic solution exploration and feedback incorporation. However, existing approaches often suffer from restricted feedback spaces and lack of coordinated training of different parties, leading to suboptimal performance. To address this, we model this multi-turn refinement process as a Markov Decision Process and introduce DPSDP (**D**irect **P**olicy **S**earch by **D**ynamic **P**rogramming), a reinforcement learning algorithm that trains an actor-critic LLM system to iteratively refine answers via direct preference learning on self-generated data. Theoretically, DPSDP can match the performance of any policy within the training distribution. Empirically, we instantiate DPSDP with various base models and show improvements on both in- and out-of-distribution benchmarks. For example, on benchmark MATH 500, majority voting over five refinement steps increases first-turn accuracy from 58.2% to 63.2% with Ministral-based models. An ablation study further confirms the benefits of multi-agent collaboration and out-of-distribution generalization.

Recent advances in Reinforcement Learning from Human Feedback (RLHF) have shown that KL-regularization plays a pivotal role in improving the efficiency of RL fine-tuning for large language models (LLMs). Despite its empirical advantage, the theoretical difference between KL-regularized RL and standard RL remains largely under-explored. While there is a recent line of work on the theoretical analysis of KL-regularized objective in decision making (Xiong et al., 2024a; Xie et al., 2024; Zhao et al., 2024), these analyses either reduce to the traditional RL setting or rely on strong coverage assumptions. In this paper, we propose an optimism-based KL-regularized online contextual bandit algorithm, and provide a novel analysis of its regret. By carefully leveraging the benign optimization landscape induced by the KL-regularization and the optimistic reward estimation, our algorithm achieves an $\mathcal{O}\big(\eta\log (N_{\mathcal R} T)\cdot d_{\mathcal R}\big)$ logarithmic regret bound, where $\eta, N_{\mathcal R},T,d_{\mathcal R}$ denote the KL-regularization parameter, the cardinality of the reward function class, number of rounds, and the complexity of the reward function class. Furthermore, we extend our algorithm and analysis to reinforcement learning by developing a novel decomposition over transition steps and also obtain a similar logarithmic regret bound.

Diffusion policies have achieved superior performance in imitation learning and offline reinforcement learning (RL) due to their rich expressiveness. However, the conventional diffusion training procedure requires samples from target distribution, which is impossible in online RL since we cannot sample from the optimal policy. Backpropagating policy gradient through the diffusion process incurs huge computational costs and instability, thus being expensive and not scalable. To enable efficient training of diffusion policies in online RL, we generalize the conventional denoising score matching by reweighting the loss function. The resulting Reweighted Score Matching (RSM) preserves the optimal solution and low computational cost of denoising score matching, while eliminating the need to sample from the target distribution and allowing learning to optimize value functions. We introduce two tractable reweighted loss functions to solve two commonly used policy optimization problems, policy mirror descent and max-entropy policy, resulting in two practical algorithms named Diffusion Policy Mirror Descent (DPMD) and Soft Diffusion Actor-Critic (SDAC). We conducted comprehensive comparisons on MuJoCo benchmarks. The empirical results show that the proposed algorithms outperform recent diffusion-policy online RLs on most tasks, and the DPMD improves more than 120% over soft actor-critic on Humanoid and Ant.

We consider a setting in which the agent aims to maximize the expected cumulative reward, subject to a constraint that the entropic risk of the total utility exceeds a given threshold. Unlike the risk-neutral case, standard primal-dual approaches fail to directly yield regret and violation bounds, as value iteration with respect to a combined state-action value function is not applicable in the risk-sensitive setting. To address this, we adopt the Optimized Certainty Equivalent (OCE) representation of the entropic risk measure and reformulate the problem by augmenting the state space with a continuous budget variable. We then propose a primal-dual algorithm tailored to this augmented formulation. In contrast to the standard approach for risk-neutral CMDPs, our method incorporates a truncated dual update to account for the possible absence of strong duality. We show that the proposed algorithm achieves regret of $\tilde{\mathcal{O}}\big(V_{g,\max}K^{3/4} + \sqrt{H^4 S^2 A \log(1/\delta)}K^{3/4}\big)$ and constraint violation of $\tilde{\mathcal{O}}\big(V_{g,\max} \sqrt{ {H^3 S^2 A \log(1/\delta)}}K^{3/4} \big)$ with probability at least $1-\delta$, where $S$ and $A$ denote the cardinalities of the state and action spaces, respectively, $H$ is the episode length, $K$ is the number of episodes, $\alpha < 0$ is the risk-aversion parameter, and $V_{g,\max} = \frac{1}{|\alpha|}(\exp(|\alpha|H) - 1)$. *To the best of our knowledge, this is the first result establishing sublinear regret and violation bounds for the risk-sensitive CMDP problem.*

Offline goal-conditioned reinforcement learning (GCRL) learns a goal-conditioned value function to train policies for diverse goals with pre-collected datasets. Hindsight experience replay addresses the issue of sparse rewards by treating intermediate states as goals but fails to complete goal-stitching tasks where achieving goals requires stitching different trajectories. While cross-trajectory sampling is a potential solution that associates states and goals belonging to different trajectories, we demonstrate that this direct method degrades performance in goal-conditioned tasks due to the overestimation of values on unconnected pairs. To this end, we propose Conservative Goal-Conditioned Implicit Value Learning (CGCIVL), a novel algorithm that introduces a penalty term to penalize value estimation for unconnected state-goal pairs and leverages the quasimetric framework to accurately estimate values for connected pairs. Evaluations on OGBench, a benchmark for offline GCRL, demonstrate that CGCIVL consistently surpasses state-of-the-art methods across diverse tasks.

Macro placement, which involves optimizing the positions of modules, is a critical phase in modern integrated circuit design and significantly influences chip performance. The growing complexity of integrated circuits demands increasingly sophisticated placement solutions. Existing approaches have evolved along two primary paths (e.g., constructive and adjustment methods), but they face significant practical limitations that affect real-world chip design. Recent hybrid frameworks such as WireMask-EA have attempted to combine these strategies, but significant technical barriers still remain, including the computational overhead from separated layout adjustment and reconstruction that often require complete layout rebuilding, the inefficient exploration of design spaces due to random mutation operations, and the computational complexity of mask-based construction methods that limit scalability. To overcome these limitations, we introduce EGPlace, a novel evolutionary optimization framework that combines guided mutation strategies with efficient layout reconstruction. EGPlace introduces two key innovations: a greedy repositioning-guided mutation operator that systematically identifies and optimizes critical layout regions, and an efficient mask computation algorithm that accelerates layout evaluation. Our extensive evaluation using ISPD2005 and Ariane RISC-V CPU benchmarks demonstrate that EGPlace reduces wirelength by \textbf{10.8\%} and \textbf{9.3\%} compared to WireMask-EA and the state-of-the-art reinforcement learning-based constructive method EfficientPlace, respectively, while achieving speedups of 7.8$\times$ and 2.8$\times$ over these methods.

Developing autonomous agents capable of performing complex, multi-step decision-making tasks specified in natural language remains a significant challenge, particularly in realistic settings where labeled data is scarce and real-time experimentation is impractical. Existing reinforcement learning (RL) approaches often struggle to generalize to unseen goals and states, limiting their applicability. In this paper, we introduce $\textit{TEDUO}$, a novel training pipeline for offline language-conditioned policy learning in symbolic environments. Unlike conventional methods, $\textit{TEDUO}$ operates on readily available, unlabeled datasets and addresses the challenge of generalization to previously unseen goals and states. Our approach harnesses large language models (LLMs) in a dual capacity: first, as automatization tools augmenting offline datasets with richer annotations, and second, as generalizable instruction-following agents. Empirical results demonstrate that $\textit{TEDUO}$ achieves data-efficient learning of robust language-conditioned policies, accomplishing tasks beyond the reach of conventional RL frameworks or out-of-the-box LLMs alone.

Offline-to-online reinforcement learning (RL) aims to integrate the complementary strengths of offline and online RL by pre-training an agent offline and subsequently fine-tuning it through online interactions. However, recent studies reveal that offline pre-trained agents often underperform during online fine-tuning due to inaccurate value estimation caused by distribution shift, with random initialization proving more effective in certain cases. In this work, we propose a novel method, Online Pre-Training for Offline-to-Online RL (OPT), explicitly designed to address the issue of inaccurate value estimation in offline pre-trained agents. OPT introduces a new learning phase, Online Pre-Training, which allows the training of a new value function tailored specifically for effective online fine-tuning. Implementation of OPT on TD3 and SPOT demonstrates an average 30\% improvement in performance across a wide range of D4RL environments, including MuJoCo, Antmaze, and Adroit.

Task robust adaptation is a long-standing pursuit in sequential decision-making. Some risk-averse strategies, e.g., the conditional value-at-risk principle, are incorporated in domain randomization or meta reinforcement learning to prioritize difficult tasks in optimization, which demand costly intensive evaluations. The efficiency issue prompts the development of robust active task sampling to train adaptive policies, where risk-predictive models can surrogate policy evaluation. This work characterizes robust active task sampling as a secret Markov decision process, posits theoretical and practical insights, and constitutes robustness concepts in risk-averse scenarios. Importantly, we propose an easy-to-implement method, referred to as Posterior and Diversity Synergized Task Sampling (PDTS), to accommodate fast and robust sequential decision-making. Extensive experiments show that PDTS unlocks the potential of robust active task sampling, significantly improves the zero-shot and few-shot adaptation robustness in challenging tasks, and even accelerates the learning process under certain scenarios.

Typical contextual bandit algorithms assume that the rewards at each round lie in some fixed range $[0, R]$, and their regret scales polynomially with this reward range $R$. However, many practical scenarios naturally involve heavy-tailed rewards or rewards where the worst-case range can be substantially larger than the variance. In this paper, we develop an algorithmic approach building on Catoni's estimator from robust statistics, and apply it to contextual bandits with general function approximation. When the variance of the reward at each round is known, we use a variance-weighted regression approach and establish a regret bound that depends only on the cumulative reward variance and logarithmically on the reward range $R$ as well as the number of rounds $T$. For the unknown-variance case, we further propose a careful peeling-based algorithm and remove the need for cumbersome variance estimation. With additional dependence on the fourth moment, our algorithm also enjoys a variance-based bound with logarithmic reward-range dependence. Moreover, we demonstrate the optimality of the leading-order term in our regret bound through a matching lower bound.

Parallel data collection has redefined Reinforcement Learning (RL), unlocking unprecedented efficiency and powering breakthroughs in large-scale real-world applications. In this paradigm, $N$ identical agents operate in $N$ replicas of an environment simulator, accelerating data collection by a factor of $N$. A critical question arises: *Does specializing the policies of the parallel agents hold the key to surpass the $N$ factor acceleration?* In this paper, we introduce a novel learning framework that maximizes the entropy of collected data in a parallel setting. Our approach carefully balances the entropy of individual agents with inter-agent diversity, effectively minimizing redundancies. The latter idea is implemented with a centralized policy gradient method, which shows promise when evaluated empirically against systems of identical agents, as well as synergy with batch RL techniques that can exploit data diversity. Finally, we provide an original concentration analysis that shows faster rates for specialized parallel sampling distributions, which supports our methodology and may be of independent interest.

Reinforcement Learning (RL) agents can solve diverse tasks but often exhibit unsafe behavior. Constrained Markov Decision Processes (CMDPs) address this by enforcing safety constraints, yet existing methods either sacrifice reward maximization or allow unsafe training. We introduce Constrained Trust Region Policy Optimization (C-TRPO), which reshapes the policy space geometry to ensure trust regions contain only safe policies, guaranteeing constraint satisfaction throughout training. We analyze its theoretical properties and connections to TRPO, Natural Policy Gradient (NPG), and Constrained Policy Optimization (CPO). Experiments show that C-TRPO reduces constraint violations while maintaining competitive returns.

Unsupervised skill discovery aims to learn diverse and distinguishable behaviors in open-ended reinforcement learning. For the existing methods, they focus on improving the diversity via pure exploration, mutual information optimization and learning temporal representation. Despite they perform well on exploration, they remain limited in terms of efficiency, especially for the high-dimensional situations. In this work, we frame the skill discovery as a min-max game of skill generation and policy learning, proposing a regret-aware method on top of temporal representation learning that expands the discovered skill space along the direction of upgradable policy strength. The key insight behind the proposed method is that the skill discovery is adversarial to the policy learning, i.e., skills with weak strength should be further explored while less exploration for the skills with converged strength. As an implementation, we score the degree of strength convergence with regret, and guide the skill discovery with a learnable skill generator. To avoid degeneration, the skill generation comes from an upgradable population of skill generators. We conduct experiments on environments with varying complexities and dimension sizes. Empirical results show that our method outperforms baselines on both efficiency and diversity. Moreover, our method achieves 15\% zero-shot improvement on high-dimensional environments, compared to existing methods.

The Conditional Sequence Modeling (CSM) paradigm, benefiting from the transformer's powerful distribution modeling capabilities, has demonstrated considerable promise in offline Reinforcement Learning (RL) tasks. Depending on the task's nature, it is crucial to carefully balance the interplay between inherent local features and long-term dependencies in Markov decision trajectories to mitigate potential performance degradation and unnecessary computational overhead. In this paper, we propose Decision Mixer (DM), which addresses the conflict between features of different scales in the modeling process from the perspective of dynamic integration. Drawing inspiration from conditional computation, we design a plug-and-play dynamic token selection mechanism to ensure the model can effectively allocate attention to different features based on task characteristics. Additionally, we employ an auxiliary predictor to alleviate the short-sightedness issue in the autoregressive sampling process. DM achieves state-of-the-art performance on various standard RL benchmarks while requiring significantly fewer computational resources, offering a viable solution for building efficient and scalable RL foundation models. Code is available at here.

Offline-to-online Reinforcement Learning (O2O RL) aims to perform online fine-tuning on an offline pre-trained policy to minimize costly online interactions. Existing work used offline datasets to generate data that conform to the online data distribution for data augmentation. However, generated data still exhibits a gap with the online data, limiting overall performance. To address this, we propose a new data augmentation approach, Classifier-Free Diffusion Generation (CFDG). Without introducing additional classifier training overhead, CFDG leverages classifier-free guidance diffusion to significantly enhance the generation quality of offline and online data with different distributions. Additionally, it employs a reweighting method to enable more generated data to align with the online data, enhancing performance while maintaining the agent's stability. Experimental results show that CFDG outperforms replaying the two data types or using a standard diffusion model to generate new data. Our method is versatile and can be integrated with existing offline-to-online RL algorithms. By implementing CFDG to popular methods IQL, PEX and APL, we achieve a notable 15\% average improvement in empirical performance on the D4RL benchmark such as MuJoCo and AntMaze.

Process and outcome supervision represent two fundamental approaches to reinforcement learning, especially for complex reasoning tasks in large language models. While process supervision offers intuitive advantages for long-term credit assignment, the precise relationship between these paradigms has remained an open question. Conventional wisdom suggests that outcome supervision is fundamentally more challenging due to the trajectory-level coverage problem, leading to significant investment in collecting fine-grained process supervision data. In this paper, we provide a possible theoretical resolution to this debate. Perhaps surprisingly, our main theorem shows that: *under standard data coverage assumptions, reinforcement learning through outcome supervision is no more statistically difficult than through process supervision*. At the core of this result lies the novel *Change of Trajectory Measure Lemma*---a powerful technical tool that bridges return-based trajectory measure and step-level distribution shift. Furthermore, for settings with access to a verifier or a rollout capability, we prove that any policy's advantage function can serve as an optimal process reward model, providing a simple yet powerful connection between outcome and process supervision. These findings suggest that the empirically observed performance gap between outcome and process supervision likely stems from algorithmic limitations rather than inherent statistical difficulties, potentially transforming how we approach data and algorithm design for reinforcement learning.

Practical reinforcement learning (RL) usually requires agents to be optimized for multiple potentially conflicting criteria, e.g. speed vs. safety. Although Multi-Objective RL (MORL) algorithms have been studied in previous works, their trained agents often cover limited Pareto optimal solutions and they lack precise controllability of the delicate trade-off among multiple objectives. Hence, the resulting agent is not versatile in aligning with customized requests from different users. To bridge the gap, we develop the ``Preference controllable (PC) RL'' framework, which trains a preference-conditioned meta-policy that takes user preference as input controlling the generated trajectories within the preference region on the Pareto frontier. The PCRL framework is compatible with advanced Multi-Objective Optimization~(MOO) algorithms that are rarely seen in previous MORL approaches. We also proposed a novel preference-regularized MOO algorithm specifically for PCRL. We provide a comprehensive theoretical analysis to justify its convergence and preference controllability. We evaluate PCRL with different MOO algorithms against state-of-the-art MORL baselines in various challenging environments with up to six objectives. In these experiments, our proposed method exhibits significantly better controllability than existing approaches and can generate Pareto solutions with better diversity and utilities.