PyTorchKR Papers

최신 논문

총 129편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2310.20266

Beyond Average Return in Markov Decision Processes

What are the functionals of the reward that can be computed and optimized exactly in Markov Decision Processes?In the finite-horizon, undiscounted setting, Dynamic Programming (DP) can only handle these operations efficiently for certain classes of statistics. We summarize the characterization of these classes for policy evaluation, and give a new answer for the planning problem. Interestingly, we prove that only generalized means can be optimized exactly, even in the more general framework of Distributional Reinforcement Learning (DistRL).DistRL permits, however, to evaluate other functionals approximately. We provide error bounds on the resulting estimators, and discuss the potential of this approach as well as its limitations.These results contribute to advancing the theory of Markov Decision Processes by examining overall characteristics of the return, and particularly risk-conscious strategies.

arXiv:2310.16546

Pitfall of Optimism: Distributional Reinforcement Learning by Randomizing Risk Criterion

Distributional reinforcement learning algorithms have attempted to utilize estimated uncertainty for exploration, such as optimism in the face of uncertainty. However, using the estimated variance for optimistic exploration may cause biased data collection and hinder convergence or performance. In this paper, we present a novel distributional reinforcement learning algorithm that selects actions by randomizing risk criterion to avoid one-sided tendency on risk. We provide a perturbed distributional Bellman optimality operator by distorting the risk measure and prove the convergence and optimality of the proposed method with the weaker contraction property. Our theoretical results support that the proposed method does not fall into biased exploration and is guaranteed to converge to an optimal return. Finally, we empirically show that our method outperforms other existing distribution-based algorithms in various environments including Atari 55 games.

arXiv:2310.05179

Distributional Reinforcement Learning with Online Risk-awareness Adaption

The use of reinforcement learning (RL) in practical applications requires considering sub-optimal outcomes, which depend on the agent's familiarity with the uncertain environment. Dynamically adjusting the level of epistemic risk over the course of learning can tactically achieve reliable optimal policy in safety-critical environments and tackle the sub-optimality of a static risk level. In this work, we introduce a novel framework, Distributional RL with Online Risk Adaption (DRL-ORA), which can quantify the aleatory and epistemic uncertainties compositely and dynamically select the epistemic risk levels via solving a total variation minimization problem online. The risk level selection can be efficiently achieved through grid search using a Follow-The-Leader type algorithm, and its offline oracle is related to "satisficing measure" (in the decision analysis community) under a special modification of the loss function. We show multiple classes of tasks where DRL-ORA outperforms existing methods that rely on either a fixed risk level or manually predetermined risk level adaption. Given the simplicity of our modifications, we believe the framework can be easily incorporated into most RL algorithm variants.

arXiv:2309.17262공식 코드 · Papers with Code

Estimation and Inference in Distributional Reinforcement Learning

In this paper, we study distributional reinforcement learning from the perspective of statistical efficiency. We investigate distributional policy evaluation, aiming to estimate the complete return distribution (denoted $\eta^\pi$) attained by a given policy $\pi$. We use the certainty-equivalence method to construct our estimator $\hat\eta^\pi$, given a generative model is available. In this circumstance we need a dataset of size $\widetilde O\left(\frac{|\mathcal{S}||\mathcal{A}|}{\varepsilon^{2p}(1-\gamma)^{2p+2}}\right)$ to guarantee the $p$-Wasserstein metric between $\hat\eta^\pi$ and $\eta^\pi$ less than $\varepsilon$ with high probability. This implies the distributional policy evaluation problem can be solved with sample efficiency. Also, we show that under different mild assumptions a dataset of size $\widetilde O\left(\frac{|\mathcal{S}||\mathcal{A}|}{\varepsilon^{2}(1-\gamma)^{4}}\right)$ suffices to ensure the Kolmogorov metric and total variation metric between $\hat\eta^\pi$ and $\eta^\pi$ is below $\varepsilon$ with high probability. Furthermore, we investigate the asymptotic behavior of $\hat\eta^\pi$. We demonstrate that the ``empirical process'' $\sqrt{n}(\hat\eta^\pi-\eta^\pi)$ converges weakly to a Gaussian process in the space of bounded functionals on Lipschitz function class $\ell^\infty(\mathcal{F}_{\text{W}})$, also in the space of bounded functionals on indicator function class $\ell^\infty(\mathcal{F}_{\text{KS}})$ and bounded measurable function class $\ell^\infty(\mathcal{F}_{\text{TV}})$ when some mild conditions hold. Our findings give rise to a unified approach to statistical inference of a wide class of statistical functionals of $\eta^\pi$.

arXiv:2309.14246

Learning Risk-Aware Quadrupedal Locomotion using Distributional Reinforcement Learning

Deployment in hazardous environments requires robots to understand the risks associated with their actions and movements to prevent accidents. Despite its importance, these risks are not explicitly modeled by currently deployed locomotion controllers for legged robots. In this work, we propose a risk sensitive locomotion training method employing distributional reinforcement learning to consider safety explicitly. Instead of relying on a value expectation, we estimate the complete value distribution to account for uncertainty in the robot's interaction with the environment. The value distribution is consumed by a risk metric to extract risk sensitive value estimates. These are integrated into Proximal Policy Optimization (PPO) to derive our method, Distributional Proximal Policy Optimization (DPPO). The risk preference, ranging from risk-averse to risk-seeking, can be controlled by a single parameter, which enables to adjust the robot's behavior dynamically. Importantly, our approach removes the need for additional reward function tuning to achieve risk sensitivity. We show emergent risk sensitive locomotion behavior in simulation and on the quadrupedal robot ANYmal. Videos of the experiments and code are available at https://sites.google.com/leggedrobotics.com/risk-aware-locomotion.

arXiv:2308.10199

Deep Reinforcement Learning for Artificial Upwelling Energy Management

The potential of artificial upwelling (AU) as a means of lifting nutrient-rich bottom water to the surface, stimulating seaweed growth, and consequently enhancing ocean carbon sequestration, has been gaining increasing attention in recent years. This has led to the development of the first solar-powered and air-lifted AU system (AUS) in China. However, efficient scheduling of air injection systems in complex marine environments remains a crucial challenge in operating AUS, as it holds the potential to significantly improve energy efficiency. To tackle this challenge, we propose a novel energy management approach that utilizes deep reinforcement learning (DRL) algorithm to develop efficient strategies for operating AUS. Specifically, we formulate the problem of maximizing the energy efficiency of AUS as a Markov decision process and integrate the quantile network in distributional reinforcement learning (QR-DQN) with the deep dueling network to solve it. Through extensive simulations, we evaluate the performance of our algorithm and demonstrate its superior effectiveness over traditional rule-based approaches and other DRL algorithms in reducing energy wastage while ensuring the stable and efficient operation of AUS. Our findings suggest that a DRL-based approach offers a promising way to improve the energy efficiency of AUS and enhance the sustainability of seaweed cultivation and carbon sequestration in the ocean.

arXiv:2308.06590공식 코드 · Papers with Code

Value-Distributional Model-Based Reinforcement Learning

Quantifying uncertainty about a policy's long-term performance is important to solve sequential decision-making tasks. We study the problem from a model-based Bayesian reinforcement learning perspective, where the goal is to learn the posterior distribution over value functions induced by parameter (epistemic) uncertainty of the Markov decision process. Previous work restricts the analysis to a few moments of the distribution over values or imposes a particular distribution shape, e.g., Gaussians. Inspired by distributional reinforcement learning, we introduce a Bellman operator whose fixed-point is the value distribution function. Based on our theory, we propose Epistemic Quantile-Regression (EQR), a model-based algorithm that learns a value distribution function. We combine EQR with soft actor-critic (SAC) for policy optimization with an arbitrary differentiable objective function of the learned value distribution. Evaluation across several continuous-control tasks shows performance benefits with respect to both model-based and model-free algorithms. The code is available at https://github.com/boschresearch/dist-mbrl.

arXiv:2307.16152공식 코드 · Papers with Code

Variance Control for Distributional Reinforcement Learning

Although distributional reinforcement learning (DRL) has been widely examined in the past few years, very few studies investigate the validity of the obtained Q-function estimator in the distributional setting. To fully understand how the approximation errors of the Q-function affect the whole training process, we do some error analysis and theoretically show how to reduce both the bias and the variance of the error terms. With this new understanding, we construct a new estimator \emph{Quantiled Expansion Mean} (QEM) and introduce a new DRL algorithm (QEMRL) from the statistical perspective. We extensively evaluate our QEMRL algorithm on a variety of Atari and Mujoco benchmark tasks and demonstrate that QEMRL achieves significant improvement over baseline algorithms in terms of sample efficiency and convergence performance.

arXiv:2307.06753

Cramer Type Distances for Learning Gaussian Mixture Models by Gradient Descent

The learning of Gaussian Mixture Models (also referred to simply as GMMs) plays an important role in machine learning. Known for their expressiveness and interpretability, Gaussian mixture models have a wide range of applications, from statistics, computer vision to distributional reinforcement learning. However, as of today, few known algorithms can fit or learn these models, some of which include Expectation-Maximization algorithms and Sliced Wasserstein Distance. Even fewer algorithms are compatible with gradient descent, the common learning process for neural networks. In this paper, we derive a closed formula of two GMMs in the univariate, one-dimensional case, then propose a distance function called Sliced Cram\'er 2-distance for learning general multivariate GMMs. Our approach has several advantages over many previous methods. First, it has a closed-form expression for the univariate case and is easy to compute and implement using common machine learning libraries (e.g., PyTorch and TensorFlow). Second, it is compatible with gradient descent, which enables us to integrate GMMs with neural networks seamlessly. Third, it can fit a GMM not only to a set of data points, but also to another GMM directly, without sampling from the target model. And fourth, it has some theoretical guarantees like global gradient boundedness and unbiased sampling gradient. These features are especially useful for distributional reinforcement learning and Deep Q Networks, where the goal is to learn a distribution over future rewards. We will also construct a Gaussian Mixture Distributional Deep Q Network as a toy example to demonstrate its effectiveness. Compared with previous models, this model is parameter efficient in terms of representing a distribution and possesses better interpretability.

arXiv:2307.01708공식 코드 · Papers with Code

Distributional Model Equivalence for Risk-Sensitive Reinforcement Learning

We consider the problem of learning models for risk-sensitive reinforcement learning. We theoretically demonstrate that proper value equivalence, a method of learning models which can be used to plan optimally in the risk-neutral setting, is not sufficient to plan optimally in the risk-sensitive setting. We leverage distributional reinforcement learning to introduce two new notions of model equivalence, one which is general and can be used to plan for any risk measure, but is intractable; and a practical variation which allows one to choose which risk measures they may plan optimally for. We demonstrate how our framework can be used to augment any model-free risk-sensitive algorithm, and provide both tabular and large-scale experiments to demonstrate its ability.

arXiv:2307.00547

Is Risk-Sensitive Reinforcement Learning Properly Resolved?

Due to the nature of risk management in learning applicable policies, risk-sensitive reinforcement learning (RSRL) has been realized as an important direction. RSRL is usually achieved by learning risk-sensitive objectives characterized by various risk measures, under the framework of distributional reinforcement learning. However, it remains unclear if the distributional Bellman operator properly optimizes the RSRL objective in the sense of risk measures. In this paper, we prove that the existing RSRL methods do not achieve unbiased optimization and can not guarantee optimality or even improvements regarding risk measures over accumulated return distributions. To remedy this issue, we further propose a novel algorithm, namely Trajectory Q-Learning (TQL), for RSRL problems with provable convergence to the optimal policy. Based on our new learning architecture, we are free to introduce a general and practical implementation for different risk measures to learn disparate risk-sensitive policies. In the experiments, we verify the learnability of our algorithm and show how our method effectively achieves better performances toward risk-sensitive objectives.

arXiv:2306.06637

PACER: A Fully Push-forward-based Distributional Reinforcement Learning Algorithm

In this paper, we propose the first fully push-forward-based distributional reinforcement learning algorithm, named PACER, which consists of a distributional critic, a stochastic actor and a sample-based encourager. Specifically, the push-forward operator is leveraged in both the critic and actor to model the return distributions and stochastic policies respectively, enabling them with equal modeling capability and thus enhancing the synergetic performance. Since it is infeasible to obtain the density function of the push-forward policies, novel sample-based regularizers are integrated in the encourager to incentivize efficient exploration and alleviate the risk of trapping into local optima. Moreover, a sample-based stochastic utility value policy gradient is established for the push-forward policy update, which circumvents the explicit demand of the policy density function in existing REINFORCE-based stochastic policy gradient. As a result, PACER fully utilizes the modeling capability of the push-forward operator and is able to explore a broader class of the policy space, compared with limited policy classes used in existing distributional actor critic algorithms (i.e. Gaussians). We validate the critical role of each component in our algorithm with extensive empirical studies. Experimental results demonstrate the superiority of our algorithm over the state-of-the-art.

arXiv:2306.07124

Diverse Projection Ensembles for Distributional Reinforcement Learning

In contrast to classical reinforcement learning (RL), distributional RL algorithms aim to learn the distribution of returns rather than their expected value. Since the nature of the return distribution is generally unknown a priori or arbitrarily complex, a common approach finds approximations within a set of representable, parametric distributions. Typically, this involves a projection of the unconstrained distribution onto the set of simplified distributions. We argue that this projection step entails a strong inductive bias when coupled with neural networks and gradient descent, thereby profoundly impacting the generalization behavior of learned models. In order to facilitate reliable uncertainty estimation through diversity, we study the combination of several different projections and representations in a distributional ensemble. We establish theoretical properties of such projection ensembles and derive an algorithm that uses ensemble disagreement, measured by the average 1-Wasserstein distance, as a bonus for deep exploration. We evaluate our algorithm on the behavior suite benchmark and VizDoom and find that diverse projection ensembles lead to significant performance improvements over existing methods on a variety of tasks with the most pronounced gains in directed exploration problems.

arXiv:2306.01925

Improving the generalizability and robustness of large-scale traffic signal control

A number of deep reinforcement-learning (RL) approaches propose to control traffic signals. In this work, we study the robustness of such methods along two axes. First, sensor failures and GPS occlusions create missing-data challenges and we show that recent methods remain brittle in the face of these missing data. Second, we provide a more systematic study of the generalization ability of RL methods to new networks with different traffic regimes. Again, we identify the limitations of recent approaches. We then propose using a combination of distributional and vanilla reinforcement learning through a policy ensemble. Building upon the state-of-the-art previous model which uses a decentralized approach for large-scale traffic signal control with graph convolutional networks (GCNs), we first learn models using a distributional reinforcement learning (DisRL) approach. In particular, we use implicit quantile networks (IQN) to model the state-action return distribution with quantile regression. For traffic signal control problems, an ensemble of standard RL and DisRL yields superior performance across different scenarios, including different levels of missing sensor data and traffic flow patterns. Furthermore, the learning scheme of the resulting model can improve zero-shot transferability to different road network structures, including both synthetic networks and real-world networks (e.g., Luxembourg, Manhattan). We conduct extensive experiments to compare our approach to multi-agent reinforcement learning and traditional transportation approaches. Results show that the proposed method improves robustness and generalizability in the face of missing data, varying road networks, and traffic flows.

arXiv:2305.18388

The Statistical Benefits of Quantile Temporal-Difference Learning for Value Estimation

We study the problem of temporal-difference-based policy evaluation in reinforcement learning. In particular, we analyse the use of a distributional reinforcement learning algorithm, quantile temporal-difference learning (QTD), for this task. We reach the surprising conclusion that even if a practitioner has no interest in the return distribution beyond the mean, QTD (which learns predictions about the full distribution of returns) may offer performance superior to approaches such as classical TD learning, which predict only the mean return, even in the tabular setting.

arXiv:2305.16877

Distributional Reinforcement Learning with Dual Expectile-Quantile Regression

Distributional reinforcement learning (RL) has proven useful in multiple benchmarks as it enables approximating the full distribution of returns and makes a better use of environment samples. The commonly used quantile regression approach to distributional RL -- based on asymmetric $L_1$ losses -- provides a flexible and effective way of learning arbitrary return distributions. In practice, it is often improved by using a more efficient, hybrid asymmetric $L_1$-$L_2$ Huber loss for quantile regression. However, by doing so, distributional estimation guarantees vanish, and we empirically observe that the estimated distribution rapidly collapses to its mean. Indeed, asymmetric $L_2$ losses, corresponding to expectile regression, cannot be readily used for distributional temporal difference learning. Motivated by the efficiency of $L_2$-based learning, we propose to jointly learn expectiles and quantiles of the return distribution in a way that allows efficient learning while keeping an estimate of the full distribution of returns. We prove that our approach approximately learns the correct return distribution, and we benchmark a practical implementation on a toy example and at scale. On the Atari benchmark, our approach matches the performance of the Huber-based IQN-1 baseline after $200$M training frames but avoids distributional collapse and keeps estimates of the full distribution of returns.

arXiv:2304.14421

One-Step Distributional Reinforcement Learning

Reinforcement learning (RL) allows an agent interacting sequentially with an environment to maximize its long-term expected return. In the distributional RL (DistrRL) paradigm, the agent goes beyond the limit of the expected value, to capture the underlying probability distribution of the return across all time steps. The set of DistrRL algorithms has led to improved empirical performance. Nevertheless, the theory of DistrRL is still not fully understood, especially in the control case. In this paper, we present the simpler one-step distributional reinforcement learning (OS-DistrRL) framework encompassing only the randomness induced by the one-step dynamics of the environment. Contrary to DistrRL, we show that our approach comes with a unified theory for both policy evaluation and control. Indeed, we propose two OS-DistrRL algorithms for which we provide an almost sure convergence analysis. The proposed approach compares favorably with categorical DistrRL on various environments.

arXiv:2303.13657

Policy Evaluation in Distributional LQR

Distributional reinforcement learning (DRL) enhances the understanding of the effects of the randomness in the environment by letting agents learn the distribution of a random return, rather than its expected value as in standard RL. At the same time, a main challenge in DRL is that policy evaluation in DRL typically relies on the representation of the return distribution, which needs to be carefully designed. In this paper, we address this challenge for a special class of DRL problems that rely on linear quadratic regulator (LQR) for control, advocating for a new distributional approach to LQR, which we call \emph{distributional LQR}. Specifically, we provide a closed-form expression of the distribution of the random return which, remarkably, is applicable to all exogenous disturbances on the dynamics, as long as they are independent and identically distributed (i.i.d.). While the proposed exact return distribution consists of infinitely many random variables, we show that this distribution can be approximated by a finite number of random variables, and the associated approximation error can be analytically bounded under mild assumptions. Using the approximate return distribution, we propose a zeroth-order policy gradient algorithm for risk-averse LQR using the Conditional Value at Risk (CVaR) as a measure of risk. Numerical experiments are provided to illustrate our theoretical results.

arXiv:2303.01768

Toward Risk-based Optimistic Exploration for Cooperative Multi-Agent Reinforcement Learning

The multi-agent setting is intricate and unpredictable since the behaviors of multiple agents influence one another. To address this environmental uncertainty, distributional reinforcement learning algorithms that incorporate uncertainty via distributional output have been integrated with multi-agent reinforcement learning (MARL) methods, achieving state-of-the-art performance. However, distributional MARL algorithms still rely on the traditional $\epsilon$-greedy, which does not take cooperative strategy into account. In this paper, we present a risk-based exploration that leads to collaboratively optimistic behavior by shifting the sampling region of distribution. Initially, we take expectations from the upper quantiles of state-action values for exploration, which are optimistic actions, and gradually shift the sampling region of quantiles to the full distribution for exploitation. By ensuring that each agent is exposed to the same level of risk, we can force them to take cooperatively optimistic actions. Our method shows remarkable performance in multi-agent settings requiring cooperative exploration based on quantile regression appropriately controlling the level of risk.

arXiv:2302.11694공식 코드 · Papers with Code

Constrained Reinforcement Learning using Distributional Representation for Trustworthy Quadrotor UAV Tracking Control

Simultaneously accurate and reliable tracking control for quadrotors in complex dynamic environments is challenging. As aerodynamics derived from drag forces and moment variations are chaotic and difficult to precisely identify, most current quadrotor tracking systems treat them as simple `disturbances' in conventional control approaches. We propose a novel, interpretable trajectory tracker integrating a Distributional Reinforcement Learning disturbance estimator for unknown aerodynamic effects with a Stochastic Model Predictive Controller (SMPC). The proposed estimator `Constrained Distributional Reinforced disturbance estimator' (ConsDRED) accurately identifies uncertainties between true and estimated values of aerodynamic effects. Simplified Affine Disturbance Feedback is used for control parameterization to guarantee convexity, which we then integrate with a SMPC. We theoretically guarantee that ConsDRED achieves at least an optimal global convergence rate and a certain sublinear rate if constraints are violated with an error decreases as the width and the layer of neural network increase. To demonstrate practicality, we show convergent training in simulation and real-world experiments, and empirically verify that ConsDRED is less sensitive to hyperparameter settings compared with canonical constrained RL approaches. We demonstrate our system improves accumulative tracking errors by at least 70% compared with the recent art. Importantly, the proposed framework, ConsDRED-SMPC, balances the tradeoff between pursuing high performance and obeying conservative constraints for practical implementations.