ICLR 2025 Papers

Learning a transition model via Maximum Likelihood Estimation (MLE) followed by planning inside the learned model is perhaps the most standard and simplest Model-based Reinforcement Learning (RL) framework. In this work, we show that such a simple Model-based RL scheme, when equipped with optimistic and pessimistic planning procedures, achieves strong regret and sample complexity bounds in online and offline RL settings. Particularly, we demonstrate that under the conditions where the trajectory-wise reward is normalized between zero and one and the transition is time-homogenous, it achieves nearly horizon-free and second-order bounds.

Dexterous hands exhibit significant potential for complex real-world grasping tasks. While recent studies have primarily focused on learning policies for specific robotic hands, the development of a universal policy that controls diverse dexterous hands remains largely unexplored. In this work, we study the learning of cross-embodiment dexterous grasping policies using reinforcement learning (RL). Inspired by the capability of human hands to control various dexterous hands through teleoperation, we propose a universal action space based on the human hand's eigengrasps. The policy outputs eigengrasp actions that are then converted into specific joint actions for each robot hand through a retargeting mapping. We simplify the robot hand's proprioception to include only the positions of fingertips and the palm, offering a unified observation space across different robot hands. Our approach demonstrates an 80\% success rate in grasping objects from the YCB dataset across four distinct embodiments using a single vision-based policy. Additionally, our policy exhibits zero-shot generalization to two previously unseen embodiments and significant improvement in efficient finetuning. For further details and videos, visit our project page (https://sites.google.com/view/crossdex).

Real-world sequential decision-making tasks often require balancing trade-offs between multiple conflicting objectives, making Multi-Objective Reinforcement Learning (MORL) an increasingly prominent field of research. Despite recent advances, existing MORL literature has narrowly focused on performance within static environments, neglecting the importance of generalizing across diverse settings. Conversely, existing research on generalization in RL has always assumed scalar rewards, overlooking the inherent multi-objectivity of real-world problems. Generalization in the multi-objective context is fundamentally more challenging, as it requires learning a Pareto set of policies addressing varying preferences across multiple objectives. In this paper, we formalize the concept of generalization in MORL and how it can be evaluated. We then contribute a novel benchmark featuring diverse multi-objective domains with parameterized environment configurations to facilitate future studies in this area. Our baseline evaluations of state-of-the-art MORL algorithms on this benchmark reveals limited generalization capabilities, suggesting significant room for improvement. Our empirical findings also expose limitations in the expressivity of scalar rewards, emphasizing the need for multi-objective specifications to achieve effective generalization. We further analyzed the algorithmic complexities within current MORL approaches that could impede the transfer in performance from the single- to multiple-environment settings. This work fills a critical gap and lays the groundwork for future research that brings together two key areas in reinforcement learning: solving multi-objective decision-making problems and generalizing across diverse environments. We make our code available at [https://github.com/JaydenTeoh/MORL-Generalization](https://github.com/JaydenTeoh/MORL-Generalization).

Intrinsic motivation and reward shaping guide reinforcement learning (RL) agents by adding pseudo-rewards, which can lead to useful emergent behaviors. However, they can also encourage counterproductive exploits, e.g., fixation with noisy TV screens. Here we provide a theoretical model which anticipates these behaviors, and provides broad criteria under which adverse effects can be bounded. We characterize all pseudo-rewards as reward shaping in Bayes-Adaptive Markov Decision Processes (BAMDPs), which formulates the problem of learning in MDPs as an MDP over the agent's knowledge. Optimal exploration maximizes BAMDP state value, which we decompose into the value of the information gathered and the prior value of the physical state. Psuedo-rewards guide RL agents by rewarding behavior that increases these value components, while they hinder exploration when they align poorly with the actual value. We extend potential-based shaping theory to prove BAMDP Potential-based shaping Functions (BAMPFs) are immune to reward-hacking (convergence to behaviors maximizing composite rewards to the detriment of real rewards) in meta-RL, and show empirically how a BAMPF helps a meta-RL agent learn optimal RL algorithms for a Bernoulli Bandit domain. We finally prove that BAMPFs with bounded monotone increasing potentials also resist reward-hacking in the regular RL setting. We show that it is straightforward to retrofit or design new pseudo-reward terms in this form, and provide an empirical demonstration in the Mountain Car environment.

Generative flow networks (GFlowNets) have been considered as powerful tools for generating candidates with desired properties. Given that evaluating the property of candidates can be complex and time-consuming, existing GFlowNets train proxy models for efficient online evaluation. However, the performance of proxy models is heavily dependent on the amount of data and is of considerable uncertainty. Therefore, it is of great interest that how to develop an offline GFlowNet that does not rely on online evaluation. Under the offline setting, the limited data results in an insufficient exploration of state space. The insufficient exploration means that offline GFlowNets can hardly generate satisfying candidates out of the distribution of training data. Therefore, it is critical to restrict the offline model to act in the distribution of training data. The distinctive training goal of GFlownets poses a unique challenge for making such restrictions. Tackling the challenge, we propose Conservative Offline GFlowNet (COFlowNet) in this paper. We define unsupported flow, edges containing unseen states in training data. Models can learn extremely little knowledge about unsupported flow from training data. By constraining the model from exploring unsupported flows, we restrict COFlowNet to explore as optimal trajectories on the training set as possible, thus generating better candidates. In order to improve the diversity of candidates, we further introduce a quantile version of unsupported flow restriction. Experimental results on several widely-used datasets validate the effectiveness of COFlowNet in generating high-scored and diverse candidates. All implementations are available at https://github.com/yuxuan9982/COflownet.

Extracting relevant information from a stream of high-dimensional observations is a central challenge for deep reinforcement learning agents. Actor-critic algorithms add further complexity to this challenge, as it is often unclear whether the same information will be relevant to both the actor and the critic. To this end, we here explore the principles that underlie effective representations for the actor and for the critic in on-policy algorithms. We focus our study on understanding whether the actor and critic will benefit from separate, rather than shared, representations. Our primary finding is that when separated, the representations for the actor and critic systematically specialise in extracting different types of information from the environment---the actor's representation tends to focus on action-relevant information, while the critic's representation specialises in encoding value and dynamics information. We conduct a rigourous empirical study to understand how different representation learning approaches affect the actor and critic's specialisations and their downstream performance, in terms of sample efficiency and generation capabilities. Finally, we discover that a separated critic plays an important role in exploration and data collection during training. Our code, trained models and data are accessible at https://github.com/francelico/deac-rep.

In this paper, we introduce a simple yet effective reward dimension reduction method to tackle the scalability challenges of multi-objective reinforcement learning algorithms. While most existing approaches focus on optimizing two to four objectives, their abilities to scale to environments with more objectives remain uncertain. Our method uses a dimension reduction approach to enhance learning efficiency and policy performance in multi-objective settings. While most traditional dimension reduction methods are designed for static datasets, our approach is tailored for online learning and preserves Pareto-optimality after transformation. We propose a new training and evaluation framework for reward dimension reduction in multi-objective reinforcement learning and demonstrate the superiority of our method in environments including one with sixteen objectives, significantly outperforming existing online dimension reduction methods.

Reinforcement learning (RL) often relies on trial and error, which may cause undesirable outcomes. As a result, standard RL is inappropriate for safety-critical applications. To address this issue, one may train a safe agent in a controlled environment (where safety violations are allowed) and then transfer it to the real world (where safety violations may have disastrous consequences). Prior work has made this transfer safe as long as the new environment preserves the safety-related dynamics. However, in most practical applications, differences or shifts in dynamics between the two environments are inevitable, potentially leading to safety violations after the transfer. This work aims to guarantee safety even when the new environment has different (safety-related) dynamics. In other words, we aim to make the process of safe transfer robust. Our methodology (1) robustifies an agent in the controlled environment and (2) provably provides---under mild assumption---a safe transfer to new environments. The empirical evaluation shows that this method yields policies that are robust against changes in dynamics, demonstrating safety after transfer to a new environment.

Reinforcement learning (RL) has shown remarkable success in training agents to achieve high-performing policies, particularly in domains like Game AI where simulation environments enable efficient interactions. However, despite their success in maximizing these returns, such online-trained policies often fail to align with human preferences concerning actions, styles, and values. The challenge lies in efficiently adapting these online-trained policies to align with human preferences, given the scarcity and high cost of collecting human behavior data. In this work, we formalize the problem as *online-to-offline* RL and propose ALIGNment of Game AI to Preferences (ALIGN-GAP), an innovative approach for the alignment of well-trained game agents to human preferences. Our method features a carefully designed reward model that encodes human preferences from limited offline data and incorporates curriculum-based preference learning to align RL agents with targeted human preferences. Experiments across diverse environments and preference types demonstrate the performance of ALIGN-GAP, achieving effective alignment with human preferences.

In the unsupervised pre-training for reinforcement learning, the agent aims to learn a prior policy for downstream tasks without relying on task-specific reward functions. We focus on state entropy maximization (SEM), where the goal is to learn a policy that maximizes the entropy of the state's stationary distribution. In this paper, we introduce SEMDICE, a principled off-policy algorithm that computes an SEM policy from an arbitrary off-policy dataset, which optimizes the policy directly within the space of stationary distributions. SEMDICE computes a single, stationary Markov state-entropy-maximizing policy from an arbitrary off-policy dataset. Experimental results demonstrate that SEMDICE outperforms baseline algorithms in maximizing state entropy while achieving the best adaptation efficiency for downstream tasks among SEM-based unsupervised RL pre-training methods.

Reinforcement learning (RL) has seen significant success across various domains, but its adoption is often limited by the black-box nature of neural network policies, making them difficult to interpret. In contrast, symbolic policies allow representing decision-making strategies in a compact and interpretable way. However, learning symbolic policies directly within on-policy methods remains challenging. In this paper, we introduce SYMPOL, a novel method for SYMbolic tree-based on-POLicy RL. SYMPOL employs a tree-based model integrated with a policy gradient method, enabling the agent to learn and adapt its actions while maintaining a high level of interpretability. We evaluate SYMPOL on a set of benchmark RL tasks, demonstrating its superiority over alternative tree-based RL approaches in terms of performance and interpretability. Unlike existing methods, it enables gradient-based, end-to-end learning of interpretable, axis-aligned decision trees within standard on-policy RL algorithms. Therefore, SYMPOL can become the foundation for a new class of interpretable RL based on decision trees. Our implementation is available under: https://github.com/s-marton/sympol

Offline reinforcement learning (RL) aims to learn from static datasets and thus faces the challenge of value estimation errors for out-of-distribution actions. The in-sample learning scheme addresses this issue by performing implicit TD backups that does not query the values of unseen actions. However, pre-existing in-sample value learning and policy extraction methods suffer from over-regularization, limiting their performance on suboptimal or compositional datasets. In this paper, we analyze key factors in in-sample learning that might potentially hinder the use of a milder constraint. We propose Actor-Critic with Temperature adjustment and In-sample Value Ensemble (ACTIVE), a novel in-sample offline RL algorithm that leverages an ensemble of $V$-functions for critic training and adaptively adjusts the constraint level using dual gradient descent. We theoretically show that the $V$-ensemble suppresses the accumulation of initial value errors, thereby mitigating overestimation. Our experiments on the D4RL benchmarks demonstrate that ACTIVE alleviates overfitting of value functions and outperforms existing in-sample methods in terms of learning stability and policy optimality.

Learning policy from offline datasets through offline reinforcement learning (RL) holds promise for scaling data-driven decision-making while avoiding unsafe and costly online interactions. However, real-world data collected from sensors or humans often contains noise and errors, posing a significant challenge for existing offline RL methods, particularly when the real-world data is limited. Our study reveals that prior research focusing on adapting predominant offline RL methods based on temporal difference learning still falls short under data corruption when the dataset is limited. In contrast, we discover that vanilla sequence modeling methods, such as Decision Transformer, exhibit robustness against data corruption, even without specialized modifications. To unlock the full potential of sequence modeling, we propose **R**obust **D**ecision **T**ransformer (**RDT**) by incorporating three simple yet effective robust techniques: embedding dropout to improve the model's robustness against erroneous inputs, Gaussian weighted learning to mitigate the effects of corrupted labels, and iterative data correction to eliminate corrupted data from the source. Extensive experiments on MuJoCo, Kitchen, and Adroit tasks demonstrate RDT's superior performance under various data corruption scenarios compared to prior methods. Furthermore, RDT exhibits remarkable robustness in a more challenging setting that combines training-time data corruption with test-time observation perturbations. These results highlight the potential of sequence modeling for learning from noisy or corrupted offline datasets, thereby promoting the reliable application of offline RL in real-world scenarios. Our code is available at https://github.com/jiawei415/RobustDecisionTransformer。

Sequential decision-making in high-dimensional continuous action spaces, particularly in stochastic environments, faces significant computational challenges. We explore this challenge in the traditional offline RL setting, where an agent must learn how to make decisions based on data collected through a stochastic behavior policy. We present \textit{Latent Macro Action Planner} (L-MAP), which addresses this challenge by learning a set of temporally extended macro-actions through a state-conditional Vector Quantized Variational Autoencoder (VQ-VAE), effectively reducing action dimensionality. L-MAP employs a (separate) learned prior model that acts as a latent transition model and allows efficient sampling of plausible actions. During planning, our approach accounts for stochasticity in both the environment and the behavior policy by using Monte Carlo tree search (MCTS). In offline RL settings, including stochastic continuous control tasks, L-MAP efficiently searches over discrete latent actions to yield high expected returns. Empirical results demonstrate that L-MAP maintains low decision latency despite increased action dimensionality. Notably, across tasks ranging from continuous control with inherently stochastic dynamics to high-dimensional robotic hand manipulation, L-MAP significantly outperforms existing model-based methods and performs on par with strong model-free actor-critic baselines, highlighting the effectiveness of the proposed approach in planning in complex and stochastic environments with high-dimensional action spaces.

Traditional multi-agent reinforcement learning (MARL) systems can develop cooperative strategies through repeated interactions. However, these systems are unable to perform well on any other setting than the one they have been trained on, and struggle to successfully cooperate with unfamiliar collaborators. This is particularly visible in the Hanabi benchmark, a popular 2-to-5 player cooperative card-game which requires complex reasoning and precise assistance to other agents. Current MARL agents for Hanabi can only learn one specific game-setting (e.g., 2-player games), and play with the same algorithmic agents. This is in stark contrast to humans, who can quickly adjust their strategies to work with unfamiliar partners or situations. In this paper, we introduce Recurrent Replay Relevance Distributed DQN (R3D2), a generalist agent for Hanabi, designed to overcome these limitations. We reformulate the task using text, as language has been shown to improve transfer. We then propose a distributed MARL algorithm that copes with the resulting dynamic observation- and action-space. In doing so, our agent is the first that can play all game settings concurrently, and extend strategies learned from one setting to other ones. As a consequence, our agent also demonstrates the ability to collaborate with different algorithmic agents ---agents that are themselves unable to do so.

Following the success of the in-context learning paradigm in large-scale language and computer vision models, the recently emerging field of in-context reinforcement learning is experiencing a rapid growth. However, its development has been held back by the lack of challenging benchmarks, as all the experiments have been carried out in simple environments and on small-scale datasets. We present **XLand-100B**, a large-scale dataset for in-context reinforcement learning based on the XLand-MiniGrid environment, as a first step to alleviate this problem. It contains complete learning histories for nearly $30,000$ different tasks, covering $100$B transitions and $2.5$B episodes. It took $50,000$ GPU hours to collect the dataset, which is beyond the reach of most academic labs. Along with the dataset, we provide the utilities to reproduce or expand it even further. We also benchmark common in-context RL baselines and show that they struggle to generalize to novel and diverse tasks. With this substantial effort, we aim to democratize research in the rapidly growing field of in-context reinforcement learning and provide a solid foundation for further scaling.

Video generative models demonstrate great promise in robotics by serving as visual planners or as policy supervisors. When pretrained on internet-scale data, such video models intimately understand alignment with natural language, and can thus facilitate generalization to novel downstream behavior through text-conditioning. However, they may not be sensitive to the specificities of the particular environment the agent inhabits. On the other hand, training video models on in-domain examples of robotic behavior naturally encodes environment-specific intricacies, but the scale of available demonstrations may not be sufficient to support generalization to unseen tasks via natural language specification. In this work, we investigate different adaptation techniques that integrate in-domain information with large-scale pretrained video models, and explore the extent to which they enable novel text-conditioned generalization for robotic tasks, while also considering their independent data and resource considerations. We successfully demonstrate across robotic environments that adapting powerful video models with small scales of example data can successfully facilitate generalization to novel behaviors. In particular, we present a novel adaptation strategy, termed *Inverse Probabilistic Adaptation*, that not only consistently achieves strong generalization performance across robotic tasks and settings, but also exhibits robustness to the quality of adaptation data, successfully solving novel tasks even when only suboptimal in-domain demonstrations are available.

Describing skills in natural language has the potential to provide an accessible way to inject human knowledge about decision-making into an AI system. We present MaestroMotif, a method for AI-assisted skill design, which yields high-performing and adaptable agents. MaestroMotif leverages the capabilities of Large Language Models (LLMs) to effectively create and reuse skills. It first uses an LLM's feedback to automatically design rewards corresponding to each skill, starting from their natural language description. Then, it employs an LLM's code generation abilities, together with reinforcement learning, for training the skills and combining them to implement complex behaviors specified in language. We evaluate MaestroMotif using a suite of complex tasks in the NetHack Learning Environment (NLE), demonstrating that it surpasses existing approaches in both performance and usability.

In real-world applications, a reinforcement learning (RL) agent should consider multiple objectives and adhere to safety guidelines. To address these considerations, we propose a constrained multi-objective RL algorithm named constrained multi-objective gradient aggregator (CoMOGA). In the field of multi-objective optimization, managing conflicts between the gradients of the multiple objectives is crucial to prevent policies from converging to local optima. It is also essential to efficiently handle safety constraints for stable training and constraint satisfaction. We address these challenges straightforwardly by treating the maximization of multiple objectives as a constrained optimization problem (COP), where the constraints are defined to improve the original objectives. Existing safety constraints are then integrated into the COP, and the policy is updated by solving the COP, which ensures the avoidance of gradient conflicts. Despite its simplicity, CoMOGA guarantees convergence to global optima in a tabular setting. Through various experiments, we have confirmed that preventing gradient conflicts is critical, and the proposed method achieves constraint satisfaction across all tasks.