NeurIPS 2024 论文列表

We explore online learning in episodic loop-free Markov decision processes on non-stationary environments (changing losses and probability transitions). Our focus is on the Concave Utility Reinforcement Learning problem (CURL), an extension of classical RL for handling convex performance criteria in state-action distributions induced by agent policies. While various machine learning problems can be written as CURL, its non-linearity invalidates traditional Bellman equations. Despite recent solutions to classical CURL, none address non-stationary MDPs. This paper introduces MetaCURL, the first CURL algorithm for non-stationary MDPs. It employs a meta-algorithm running multiple black-box algorithms instances over different intervals, aggregating outputs via a sleeping expert framework. The key hurdle is partial information due to MDP uncertainty. Under partial information on the probability transitions (uncertainty and non-stationarity coming only from external noise, independent of agent state-action pairs), we achieve optimal dynamic regret without prior knowledge of MDP changes. Unlike approaches for RL, MetaCURL handles full adversarial losses, not just stochastic ones. We believe our approach for managing non-stationarity with experts can be of interest to the RL community.

Learning safe policies has presented a longstanding challenge for the reinforcement learning (RL) community. Various formulations of safe RL have been proposed; However, fundamentally, tabula rasa RL must learn safety constraints through experience, which is problematic for real-world applications. Imitation learning is often preferred in real-world settings because the experts' safety preferences are embedded in the data the agent imitates. However, imitation learning is limited in its extensibility to new tasks, which can only be learned by providing the agent with expert trajectories. For safety-critical applications with sub-optimal or inexact expert data, it would be preferable to learn only the safety aspects of the policy through imitation, while still allowing for task learning with RL. The field of inverse constrained RL, which seeks to infer constraints from expert data, is a promising step in this direction. However, prior work in this area has relied on complex tri-level optimizations in order to infer safe behavior (constraints). This challenging optimization landscape leads to sub-optimal performance on several benchmark tasks. In this work, we present a simplified version of constraint inference that performs as well or better than prior work across a collection of continuous-control benchmarks. Moreover, besides improving performance, this simplified framework is easier to implement, tune, and more readily lends itself to various extensions, such as offline constraint inference.

Techniques that learn improved representations via offline data or self-supervised objectives have shown impressive results in traditional reinforcement learning. Nevertheless, it is unclear how improved representation learning can benefit reinforcement learning from human feedback on language models. In this work, we propose training reward models (RMs) in a contrastive, $\textit{goal-conditioned}$ fashion by increasing the representation similarity of future states along sampled preferred trajectories and decreasing the similarity along randomly sampled dispreferred trajectories. This objective significantly improves reward model performance by up to 0.09 AUROC across challenging benchmarks, such as MATH and GSM8k. These findings extend to general alignment as well -- on the Helpful-Harmless dataset, we observe 2.3\% increase in accuracy. Beyond improving reward model performance, we show this way of training RM representations enables improved steerability because it allows us to evaluate the likelihood of an action achieving a particular goal-state (e.g. whether a solution is correct or helpful). Leveraging this insight, we find that we can filter up to 55\% of generated tokens during majority voting by discarding trajectories likely to end up in an "incorrect" state, which leads to significant cost savings. We additionally find that these representations can perform fine-grained control by conditioning on desired future goal-states. For example, we show that steering a Llama 3 model towards helpful generations with our approach improves helpfulness by $9.6$\% over a supervised-fine-tuning trained baseline. Similarly, steering the model towards complex generations improves complexity by $21.6$\% over the baseline. Overall, we find that training RMs in this contrastive, goal-conditioned fashion significantly improves performance and enables model steerability.

In this work, we study the \textit{state-free RL} problem, where the algorithm does not have the states information before interacting with the environment. Specifically, denote the reachable state set by $\mathcal{S}^\Pi := \{ s|\max_{\pi\in \Pi}q^{P, \pi}(s)>0 \}$, we design an algorithm which requires no information on the state space $S$ while having a regret that is completely independent of $\mathcal{S}$ and only depend on $\mathcal{S}^\Pi$. We view this as a concrete first step towards \textit{parameter-free RL}, with the goal of designing RL algorithms that require no hyper-parameter tuning.

In recent years, significant attention has been directed towards learning average-reward Markov Decision Processes (MDPs). However, existing algorithms either suffer from sub-optimal regret guarantees or computational inefficiencies. In this paper, we present the first *tractable* algorithm with minimax optimal regret of $\mathrm{O}\left(\sqrt{\mathrm{sp}(h^*) S A T \log(SAT)}\right)$ where $\mathrm{sp}(h^*)$ is the span of the optimal bias function $h^*$, $S\times A$ is the size of the state-action space and $T$ the number of learning steps. Remarkably, our algorithm does not require prior information on $\mathrm{sp}(h^*)$. Our algorithm relies on a novel subroutine, **P**rojected **M**itigated **E**xtended **V**alue **I**teration (`PMEVI`), to compute bias-constrained optimal policies efficiently. This subroutine can be applied to various previous algorithms to obtain improved regret bounds.

One of the fundamental challenges for offline reinforcement learning (RL) is ensuring robustness to data distribution. Whether the data originates from a near-optimal policy or not, we anticipate that an algorithm should demonstrate its ability to learn an effective control policy that seamlessly aligns with the inherent distribution of offline data. Unfortunately, behavior regularization, a simple yet effective offline RL algorithm, tends to struggle in this regard. In this paper, we propose a new algorithm that substantially enhances behavior-regularization based on conservative policy iteration. Our key observation is that by iteratively refining the reference policy used for behavior regularization, conservative policy update guarantees gradually improvement, while also implicitly avoiding querying out-of-sample actions to prevent catastrophic learning failures. We prove that in the tabular setting this algorithm is capable of learning the optimal policy covered by the offline dataset, commonly referred to as the in-sample optimal policy. We then explore several implementation details of the algorithm when function approximations are applied. The resulting algorithm is easy to implement, requiring only a few lines of code modification to existing methods. Experimental results on the D4RL benchmark indicate that our method outperforms previous state-of-the-art baselines in most tasks, clearly demonstrate its superiority over behavior regularization.

Plasticity loss, trainability loss, and primacy bias have been identified as issues arising when training deep neural networks on sequences of tasks---referring to the increased difficulty in training on new tasks. We propose to use Parseval regularization, which maintains orthogonality of weight matrices, to preserve useful optimization properties and improve training in a continual reinforcement learning setting. We show that it provides significant benefits to RL agents on a suite of gridworld, CARL and MetaWorld tasks. We conduct comprehensive ablations to identify the source of its benefits and investigate the effect of certain metrics associated to network trainability including weight matrix rank, weight norms and policy entropy.

Recently, Model-based Reinforcement Learning (MBRL) methods have demonstrated stunning sample efficiency in various RL domains. However, achieving this extraordinary sample efficiency comes with additional training costs in terms of computations, memory, and training time. To address these challenges, we propose the **Pa**rallelized **Mo**del-based **R**einforcement **L**earning (**PaMoRL**) framework. PaMoRL introduces two novel techniques: the **P**arallel **W**orld **M**odel (**PWM**) and the **P**arallelized **E**ligibility **T**race **E**stimation (**PETE**) to parallelize both model learning and policy learning stages of current MBRL methods over the sequence length. Our PaMoRL framework is hardware-efficient and stable, and it can be applied to various tasks with discrete or continuous action spaces using a single set of hyperparameters. The empirical results demonstrate that the PWM and PETE within PaMoRL significantly increase training speed without sacrificing inference efficiency. In terms of sample efficiency, PaMoRL maintains an MBRL-level sample efficiency that outperforms other no-look-ahead MBRL methods and model-free RL methods, and it even exceeds the performance of planning-based MBRL methods and methods with larger networks in certain tasks.

Enhancing exploration in reinforcement learning (RL) through the incorporation of intrinsic rewards, specifically by leveraging *state discrepancy* measures within various metric spaces as exploration bonuses, has emerged as a prevalent strategy to encourage agents to visit novel states. The critical factor lies in how to quantify the difference between adjacent states as *novelty* for promoting effective exploration. Nonetheless, existing methods that evaluate state discrepancy in the latent space under $L_1$ or $L_2$ norm often depend on count-based episodic terms as scaling factors for exploration bonuses, significantly limiting their scalability. Additionally, methods that utilize the bisimulation metric for evaluating state discrepancies face a theory-practice gap due to improper approximations in metric learning, particularly struggling with *hard exploration* tasks. To overcome these challenges, we introduce the **E**ffective **M**etric-based **E**xploration-bonus (EME). EME critically examines and addresses the inherent limitations and approximation inaccuracies of current metric-based state discrepancy methods for exploration, proposing a robust metric for state discrepancy evaluation backed by comprehensive theoretical analysis. Furthermore, we propose the diversity-enhanced scaling factor integrated into the exploration bonus to be dynamically adjusted by the variance of prediction from an ensemble of reward models, thereby enhancing exploration effectiveness in particularly challenging scenarios. Extensive experiments are conducted on hard exploration tasks within Atari games, Minigrid, Robosuite, and Habitat, which illustrate our method's scalability to various scenarios. The project website can be found at https://sites.google.com/view/effective-metric-exploration.

Achieving the no-regret property for Reinforcement Learning (RL) problems in continuous state and action-space environments is one of the major open problems in the field. Existing solutions either work under very specific assumptions or achieve bounds that are vacuous in some regimes. Furthermore, many structural assumptions are known to suffer from a provably unavoidable exponential dependence on the time horizon $H$ in the regret, which makes any possible solution unfeasible in practice. In this paper, we identify _local linearity_ as the feature that makes Markov Decision Processes (MDPs) both _learnable_ (sublinear regret) and _feasible_ (regret that is polynomial in $H$). We define a novel MDP representation class, namely _Locally Linearizable MDPs_, generalizing other representation classes like Linear MDPs and MDPS with low inherent Belmman error. Then, i) we introduce **Cinderella**, a no-regret algorithm for this general representation class, and ii) we show that all known learnable and feasible MDP families are representable in this class. We first show that all known feasible MDPs belong to a family that we call _Mildly Smooth MDPs_. Then, we show how any mildly smooth MDP can be represented as a Locally Linearizable MDP by an appropriate choice of representation. This way, **Cinderella** is shown to achieve state-of-the-art regret bounds for all previously known (and some new) continuous MDPs for which RL is learnable and feasible.

We introduce DynaMITE-RL, a meta-reinforcement learning (meta-RL) approach to approximate inference in environments where the latent state evolves at varying rates. We model episode sessions---parts of the episode where the latent state is fixed---and propose three key modifications to existing meta-RL methods: (i) consistency of latent information within sessions, (ii) session masking, and (iii) prior latent conditioning. We demonstrate the importance of these modifications in various domains, ranging from discrete Gridworld environments to continuous-control and simulated robot assistive tasks, illustrating the efficacy of DynaMITE-RL over state-of-the-art baselines in both online and offline RL settings.

Current approaches to model-based offline reinforcement learning often incorporate uncertainty-based reward penalization to address the distributional shift problem. These approaches, commonly known as pessimistic value iteration, use Monte Carlo sampling to estimate the Bellman target to perform temporal difference-based policy evaluation. We find out that the randomness caused by this sampling step significantly delays convergence. We present a theoretical result demonstrating the strong dependency of suboptimality on the number of Monte Carlo samples taken per Bellman target calculation. Our main contribution is a deterministic approximation to the Bellman target that uses progressive moment matching, a method developed originally for deterministic variational inference. The resulting algorithm, which we call Moment Matching Offline Model-Based Policy Optimization (MOMBO), propagates the uncertainty of the next state through a nonlinear Q-network in a deterministic fashion by approximating the distributions of hidden layer activations by a normal distribution. We show that it is possible to provide tighter guarantees for the suboptimality of MOMBO than the existing Monte Carlo sampling approaches. We also observe MOMBO to converge faster than these approaches in a large set of benchmark tasks.

Data augmentation creates new data points by transforming the original ones for an reinforcement learning (RL) agent to learn from, which has been shown to be effective for the objective of improving data efficiency of RL for continuous control. Prior work towards this objective has been largely restricted to perturbation-based data augmentation where new data points are created by perturbing the original ones, which has been impressively effective for tasks where the RL agent observe control states as images with perturbations including random cropping, shifting, etc. This work focuses on state-based control, where the RL agent can directly observe raw kinematic and task features, and considers an alternative data augmentation applied to these features based on Euclidean symmetries under transformations like rotations. We show that the default state features used in exiting benchmark tasks that are based on joint configurations are not amenable to Euclidean transformations. We therefore advocate using state features based on configurations of the limbs (i.e., rigid bodies connected by joints) that instead provides rich augmented data under Euclidean transformations. With minimal hyperparameter tuning, we show this new Euclidean data augmentation strategy significantly improve both data efficiency and asymptotic performance of RL on a wide range of continuous control tasks.

Leveraging the depth and flexibility of XLand as well as the rapid prototyping features of the Unity engine, we present the United Unity Universe — an open-source toolkit designed to accelerate the creation of innovative reinforcement learning environments. This toolkit includes a robust implementation of XLand 2.0 complemented by a user-friendly interface which allows users to modify the details of procedurally generated terrains and task rules with ease. Additionally, we provide a curated selection of terrains and rule sets, accompanied by implementations of reinforcement learning baselines to facilitate quick experimentation with novel architectural designs for adaptive agents. Furthermore, we illustrate how the United Unity Universe serves as a high-level language that enables researchers to develop diverse and endlessly variable 3D environments within a unified framework. This functionality establishes the United Unity Universe (U3) as an essential tool for advancing the field of reinforcement learning, especially in the development of adaptive and generalizable learning systems.

Robust reinforcement learning is essential for deploying reinforcement learning algorithms in real-world scenarios where environmental uncertainty predominates. Traditional robust reinforcement learning often depends on rectangularity assumptions, where adverse probability measures of outcome states are assumed to be independent across different states and actions. This assumption, rarely fulfilled in practice, leads to overly conservative policies. To address this problem, we introduce a new time-constrained robust MDP (TC-RMDP) formulation that considers multifactorial, correlated, and time-dependent disturbances, thus more accurately reflecting real-world dynamics. This formulation goes beyond the conventional rectangularity paradigm, offering new perspectives and expanding the analytical framework for robust RL. We propose three distinct algorithms, each using varying levels of environmental information, and evaluate them extensively on continuous control benchmarks. Our results demonstrate that these algorithms yield an efficient tradeoff between performance and robustness, outperforming traditional deep robust RL methods in time-constrained environments while preserving robustness in classical benchmarks. This study revisits the prevailing assumptions in robust RL and opens new avenues for developing more practical and realistic RL applications.

``Distribution shift'' is the primary obstacle to the success of offline reinforcement learning. As a learning policy may take actions beyond the knowledge of the behavior policy (referred to as Out-of-Distribution (OOD) actions), the Q-values of these OOD actions can be easily overestimated. Consequently, the learning policy becomes biasedly optimized using the incorrect recovered Q-value function. One commonly used idea to avoid the overestimation of Q-value is to make a pessimistic adjustment. Our key idea is to penalize the Q-values of OOD actions that correspond to high uncertainty. In this work, we propose Q-Distribution guided Q-learning (QDQ) which pessimistic Q-value on OOD regions based on uncertainty estimation. The uncertainty measure is based on the conditional Q-value distribution, which is learned via a high-fidelity and efficient consistency model. On the other hand, to avoid the overly conservative problem, we introduce an uncertainty-aware optimization objective to update the Q-value function. The proposed QDQ demonstrates solid theoretical guarantees for the accuracy of Q-value distribution learning and uncertainty measurement, as well as the performance of the learning policy. QDQ consistently exhibits strong performance in the D4RL benchmark and shows significant improvements for many tasks. Our code can be found at <code link>.

Continual learning with deep neural networks presents challenges distinct from both the fixed-dataset and convex continual learning regimes. One such challenge is plasticity loss, wherein a neural network trained in an online fashion displays a degraded ability to fit new tasks. This problem has been extensively studied in both supervised learning and off-policy reinforcement learning (RL), where a number of remedies have been proposed. Still, plasticity loss has received less attention in the on-policy deep RL setting. Here we perform an extensive set of experiments examining plasticity loss and a variety of mitigation methods in on-policy deep RL. We demonstrate that plasticity loss is pervasive under domain shift in this regime, and that a number of methods developed to resolve it in other settings fail, sometimes even performing worse than applying no intervention at all. In contrast, we find that a class of ``regenerative'' methods are able to consistently mitigate plasticity loss in a variety of contexts, including in gridworld tasks and more challenging environments like Montezuma's Revenge and ProcGen.

Reinforcement Learning (RL) is a powerful method for controlling dynamic systems, but its learning mechanism can lead to unpredictable actions that undermine the safety of critical systems. Here, we propose RL with Adaptive Regularization (RL-AR), an algorithm that enables safe RL exploration by combining the RL policy with a policy regularizer that hard-codes the safety constraints. RL-AR performs policy combination via a "focus module," which determines the appropriate combination depending on the state—relying more on the safe policy regularizer for less-exploited states while allowing unbiased convergence for well-exploited states. In a series of critical control applications, we demonstrate that RL-AR not only ensures safety during training but also achieves a return competitive with the standards of model-free RL that disregards safety.

Data selection is essential for training deep learning models. An effective data sampler assigns proper sampling probability for training data and helps the model converge to a good local minimum with high performance. Previous studies in data sampling are mainly based on heuristic rules or learning through a huge amount of time-consuming trials. In this paper, we propose an automatic swift sampler search algorithm, SS, to explore automatically learning effective samplers efficiently. In particular, SS utilizes a novel formulation to map a sampler to a low dimension of hyper-parameters and uses an approximated local minimum to quickly examine the quality of a sampler. Benefiting from its low computational expense, SS can be applied on large-scale data sets with high efficiency. Comprehensive experiments on various tasks demonstrate that SS powered sampling can achieve obvious improvements (e.g., 1.5% on ImageNet) and transfer among different neural networks. Project page: https://github.com/Alexander-Yao/Swift-Sampler.