Offline reinforcement learning aims to train a policy on a pre-recorded and fixed dataset without any additional environment interactions. There are two major challenges in this setting: (1) extrapolation error caused by approximating the value of state-action pairs not well-covered by the training data and (2) distributional shift between behavior and inference policies. One way to tackle these problems is to induce conservatism - i.e., keeping the learned policies closer to the behavioral ones. To achieve this, we build upon recent works on learning policies in latent action spaces and use a special form of Normalizing Flows for constructing a generative model, which we use as a conservative action encoder. This Normalizing Flows action encoder is pre-trained in a supervised manner on the offline dataset, and then an additional policy model - controller in the latent space - is trained via reinforcement learning. This approach avoids querying actions outside of the training dataset and therefore does not require additional regularization for out-of-dataset actions. We evaluate our method on various locomotion and navigation tasks, demonstrating that our approach outperforms recently proposed algorithms with generative action models on a large portion of datasets.
相關內容
Consider this scenario: an agent navigates a latent graph by performing actions that take it from one node to another. The chosen action determines the probability distribution over the next visited node. At each node, the agent receives an observation, but this observation is not unique, so it does not identify the node, making the problem aliased. The purpose of this work is to provide a policy that approximately maximizes exploration efficiency (i.e., how well the graph is recovered for a given exploration budget). In the unaliased case, we show improved performance w.r.t. state-of-the-art reinforcement learning baselines. For the aliased case we are not aware of suitable baselines and instead show faster recovery w.r.t. a random policy for a wide variety of topologies, and exponentially faster recovery than a random policy for challenging topologies. We dub the algorithm eFeX (from eFficient eXploration).
Inverse Reinforcement Learning (IRL) is a powerful paradigm for inferring a reward function from expert demonstrations. Many IRL algorithms require a known transition model and sometimes even a known expert policy, or they at least require access to a generative model. However, these assumptions are too strong for many real-world applications, where the environment can be accessed only through sequential interaction. We propose a novel IRL algorithm: Active exploration for Inverse Reinforcement Learning (AceIRL), which actively explores an unknown environment and expert policy to quickly learn the expert's reward function and identify a good policy. AceIRL uses previous observations to construct confidence intervals that capture plausible reward functions and find exploration policies that focus on the most informative regions of the environment. AceIRL is the first approach to active IRL with sample-complexity bounds that does not require a generative model of the environment. AceIRL matches the sample complexity of active IRL with a generative model in the worst case. Additionally, we establish a problem-dependent bound that relates the sample complexity of AceIRL to the suboptimality gap of a given IRL problem. We empirically evaluate AceIRL in simulations and find that it significantly outperforms more naive exploration strategies.
We are witnessing significant progress on perception models, specifically those trained on large-scale internet images. However, efficiently generalizing these perception models to unseen embodied tasks is insufficiently studied, which will help various relevant applications (e.g., home robots). Unlike static perception methods trained on pre-collected images, the embodied agent can move around in the environment and obtain images of objects from any viewpoints. Therefore, efficiently learning the exploration policy and collection method to gather informative training samples is the key to this task. To do this, we first build a 3D semantic distribution map to train the exploration policy self-supervised by introducing the semantic distribution disagreement and the semantic distribution uncertainty rewards. Note that the map is generated from multi-view observations and can weaken the impact of misidentification from an unfamiliar viewpoint. Our agent is then encouraged to explore the objects with different semantic distributions across viewpoints, or uncertain semantic distributions. With the explored informative trajectories, we propose to select hard samples on trajectories based on the semantic distribution uncertainty to reduce unnecessary observations that can be correctly identified. Experiments show that the perception model fine-tuned with our method outperforms the baselines trained with other exploration policies. Further, we demonstrate the robustness of our method in real-robot experiments.
Applying reinforcement learning (RL) to traffic signal control (TSC) has become a promising solution. However, most RL-based methods focus solely on optimization within simulators and give little thought to deployment issues in the real world. Online RL-based methods, which require interaction with the environment, are limited in their interactions with the real-world environment. Additionally, acquiring an offline dataset for offline RL is challenging in the real world. Moreover, most real-world intersections prefer a cyclical phase structure. To address these challenges, we propose: (1) a cyclical offline dataset (COD), designed based on common real-world scenarios to facilitate easy collection; (2) an offline RL model called DataLight, capable of learning satisfactory control strategies from the COD; and (3) a method called Arbitrary To Cyclical (ATC), which can transform most RL-based methods into cyclical signal control. Extensive experiments using real-world datasets on simulators demonstrate that: (1) DataLight outperforms most existing methods and achieves comparable results with the best-performing method; (2) introducing ATC into some recent RL-based methods achieves satisfactory performance; and (3) COD is reliable, with DataLight remaining robust even with a small amount of data. These results suggest that the cyclical offline dataset might be enough for offline RL for TSC. Our proposed methods make significant contributions to the TSC field and successfully bridge the gap between simulation experiments and real-world applications. Our code is released on Github.
We consider network games where a large number of agents interact according to a network sampled from a random network model, represented by a graphon. By exploiting previous results on convergence of such large network games to graphon games, we examine a procedure for estimating unknown payoff parameters, from observations of equilibrium actions, without the need for exact network information. We prove smoothness and local convexity of the optimization problem involved in computing the proposed estimator. Additionally, under a notion of graphon parameter identifiability, we show that the optimal estimator is globally unique. We present several examples of identifiable homogeneous and heterogeneous parameters in different classes of linear quadratic network games with numerical simulations to validate the proposed estimator.
This paper is concerned with the sample efficiency of reinforcement learning, assuming access to a generative model (or simulator). We first consider $\gamma$-discounted infinite-horizon Markov decision processes (MDPs) with state space $\mathcal{S}$ and action space $\mathcal{A}$. Despite a number of prior works tackling this problem, a complete picture of the trade-offs between sample complexity and statistical accuracy is yet to be determined. In particular, all prior results suffer from a severe sample size barrier, in the sense that their claimed statistical guarantees hold only when the sample size exceeds at least $\frac{|\mathcal{S}||\mathcal{A}|}{(1-\gamma)^2}$. The current paper overcomes this barrier by certifying the minimax optimality of two algorithms -- a perturbed model-based algorithm and a conservative model-based algorithm -- as soon as the sample size exceeds the order of $\frac{|\mathcal{S}||\mathcal{A}|}{1-\gamma}$ (modulo some log factor). Moving beyond infinite-horizon MDPs, we further study time-inhomogeneous finite-horizon MDPs, and prove that a plain model-based planning algorithm suffices to achieve minimax-optimal sample complexity given any target accuracy level. To the best of our knowledge, this work delivers the first minimax-optimal guarantees that accommodate the entire range of sample sizes (beyond which finding a meaningful policy is information theoretically infeasible).
Autoencoders have demonstrated remarkable success in learning low-dimensional latent features of high-dimensional data across various applications. Assuming that data are sampled near a low-dimensional manifold, we employ chart autoencoders, which encode data into low-dimensional latent features on a collection of charts, preserving the topology and geometry of the data manifold. Our paper establishes statistical guarantees on the generalization error of chart autoencoders, and we demonstrate their denoising capabilities by considering $n$ noisy training samples, along with their noise-free counterparts, on a $d$-dimensional manifold. By training autoencoders, we show that chart autoencoders can effectively denoise the input data with normal noise. We prove that, under proper network architectures, chart autoencoders achieve a squared generalization error in the order of $\displaystyle n^{-\frac{2}{d+2}}\log^4 n$, which depends on the intrinsic dimension of the manifold and only weakly depends on the ambient dimension and noise level. We further extend our theory on data with noise containing both normal and tangential components, where chart autoencoders still exhibit a denoising effect for the normal component. As a special case, our theory also applies to classical autoencoders, as long as the data manifold has a global parametrization. Our results provide a solid theoretical foundation for the effectiveness of autoencoders, which is further validated through several numerical experiments.
Classic algorithms and machine learning systems like neural networks are both abundant in everyday life. While classic computer science algorithms are suitable for precise execution of exactly defined tasks such as finding the shortest path in a large graph, neural networks allow learning from data to predict the most likely answer in more complex tasks such as image classification, which cannot be reduced to an exact algorithm. To get the best of both worlds, this thesis explores combining both concepts leading to more robust, better performing, more interpretable, more computationally efficient, and more data efficient architectures. The thesis formalizes the idea of algorithmic supervision, which allows a neural network to learn from or in conjunction with an algorithm. When integrating an algorithm into a neural architecture, it is important that the algorithm is differentiable such that the architecture can be trained end-to-end and gradients can be propagated back through the algorithm in a meaningful way. To make algorithms differentiable, this thesis proposes a general method for continuously relaxing algorithms by perturbing variables and approximating the expectation value in closed form, i.e., without sampling. In addition, this thesis proposes differentiable algorithms, such as differentiable sorting networks, differentiable renderers, and differentiable logic gate networks. Finally, this thesis presents alternative training strategies for learning with algorithms.
Model-agnostic meta-learners aim to acquire meta-learned parameters from similar tasks to adapt to novel tasks from the same distribution with few gradient updates. With the flexibility in the choice of models, those frameworks demonstrate appealing performance on a variety of domains such as few-shot image classification and reinforcement learning. However, one important limitation of such frameworks is that they seek a common initialization shared across the entire task distribution, substantially limiting the diversity of the task distributions that they are able to learn from. In this paper, we augment MAML with the capability to identify the mode of tasks sampled from a multimodal task distribution and adapt quickly through gradient updates. Specifically, we propose a multimodal MAML (MMAML) framework, which is able to modulate its meta-learned prior parameters according to the identified mode, allowing more efficient fast adaptation. We evaluate the proposed model on a diverse set of few-shot learning tasks, including regression, image classification, and reinforcement learning. The results not only demonstrate the effectiveness of our model in modulating the meta-learned prior in response to the characteristics of tasks but also show that training on a multimodal distribution can produce an improvement over unimodal training.
Meta-reinforcement learning algorithms can enable robots to acquire new skills much more quickly, by leveraging prior experience to learn how to learn. However, much of the current research on meta-reinforcement learning focuses on task distributions that are very narrow. For example, a commonly used meta-reinforcement learning benchmark uses different running velocities for a simulated robot as different tasks. When policies are meta-trained on such narrow task distributions, they cannot possibly generalize to more quickly acquire entirely new tasks. Therefore, if the aim of these methods is to enable faster acquisition of entirely new behaviors, we must evaluate them on task distributions that are sufficiently broad to enable generalization to new behaviors. In this paper, we propose an open-source simulated benchmark for meta-reinforcement learning and multi-task learning consisting of 50 distinct robotic manipulation tasks. Our aim is to make it possible to develop algorithms that generalize to accelerate the acquisition of entirely new, held-out tasks. We evaluate 6 state-of-the-art meta-reinforcement learning and multi-task learning algorithms on these tasks. Surprisingly, while each task and its variations (e.g., with different object positions) can be learned with reasonable success, these algorithms struggle to learn with multiple tasks at the same time, even with as few as ten distinct training tasks. Our analysis and open-source environments pave the way for future research in multi-task learning and meta-learning that can enable meaningful generalization, thereby unlocking the full potential of these methods.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191