论文检索

Reinforcement Learning/Planning

Sarath Sreedharan, Michael Katz

There has been an increasing interest in using symbolic models along with reinforcement learning (RL) problems, where these coarser abstract models are used as a way to provide RL agents with higher level guidance. However, most of these works are inherently limited by their assumption of having an access to a symbolic approximation of the underlying problem. To address this issue, we introduce a new method for learning optimistic symbolic approximations of the underlying world model. We will see how these representations, coupled with fast diverse planners developed by the automated planning community, provide us with a new paradigm for optimistic exploration in sparse reward settings. We investigate the possibility of speeding up the learning process by generalizing learned model dynamics across similar actions with minimal human input. Finally, we evaluate the method, by testing it on multiple benchmark domains and compare it with other RL strategies.

Theory/Reinforcement Learning and Planning

Han Shao, Lee Cohen, Avrim Blum, Yishay Mansour, Aadirupa Saha, Matthew Walter

In this work, we propose a multi-objective decision making framework that accommodates different user preferences over objectives, where preferences are learned via policy comparisons. Our model consists of a known Markov decision process with a vector-valued reward function, with each user having an unknown preference vector that expresses the relative importance of each objective. The goal is to efficiently compute a near-optimal policy for a given user. We consider two user feedback models. We first address the case where a user is provided with two policies and returns their preferred policy as feedback. We then move to a different user feedback model, where a user is instead provided with two small weighted sets of representative trajectories and selects the preferred one. In both cases, we suggest an algorithm that finds a nearly optimal policy for the user using a number of comparison queries that scales quasilinearly in the number of objectives.

Yilun Du, Sherry Yang, Bo Dai, Hanjun Dai, Ofir Nachum, Josh Tenenbaum, Dale Schuurmans, Pieter Abbeel

A goal of artificial intelligence is to construct an agent that can solve a wide variety of tasks. Recent progress in text-guided image synthesis has yielded models with an impressive ability to generate complex novel images, exhibiting combinatorial generalization across domains. Motivated by this success, we investigate whether such tools can be used to construct more general-purpose agents. Specifically, we cast the sequential decision making problem as a text-conditioned video generation problem, where, given a text-encoded specification of a desired goal, a planner synthesizes a set of future frames depicting its planned actions in the future, after which control actions are extracted from the generated video. By leveraging text as the underlying goal specification, we are able to naturally and combinatorially generalize to novel goals. The proposed policy-as-video formulation can further represent environments with different state and action spaces in a unified space of images, which, for example, enables learning and generalization across a variety of robot manipulation tasks. Finally, by leveraging pretrained language embeddings and widely available videos from the internet, the approach enables knowledge transfer through predicting highly realistic video plans for real robots.

Applications/Robotics

Jiayuan Mao, Tomás Lozano-Pérez, Josh Tenenbaum, Leslie Kaelbling

Goal-conditioned policies are generally understood to be "feed-forward" circuits, in the form of neural networks that map from the current state and the goal specification to the next action to take. However, under what circumstances such a policy can be learned and how efficient the policy will be are not well understood. In this paper, we present a circuit complexity analysis for relational neural networks (such as graph neural networks and transformers) representing policies for planning problems, by drawing connections with serialized goal regression search (S-GRS). We show that there are three general classes of planning problems, in terms of the growth of circuit width and depth as a function of the number of objects and planning horizon, providing constructive proofs. We also illustrate the utility of this analysis for designing neural networks for policy learning.

Reinforcement Learning/Deep RL

Shengran Hu, Jeff Clune

Language is often considered a key aspect of human thinking, providing us with exceptional abilities to generalize, explore, plan, replan, and adapt to new situations. However, Reinforcement Learning (RL) agents are far from human-level performance in any of these abilities. We hypothesize one reason for such cognitive deficiencies is that they lack the benefits of thinking in language and that we can improve AI agents by training them to $\textit{think like humans do}$. We introduce a novel Imitation Learning framework, Thought Cloning, where the idea is to not just clone the behaviors of human demonstrators, $\textit{but also the thoughts humans have as they perform these behaviors}$. While we expect Thought Cloning to truly shine at scale on internet-sized datasets (e.g. online videos with transcripts), here we conduct experiments in a domain where the thinking and action data are synthetically generated. Results reveal that Thought Cloning learns much faster than Behavioral Cloning and its performance advantage grows the further out of distribution test tasks are, highlighting its ability to better handle novel situations. Thought Cloning also provides important benefits for AI Safety and Interpretability, and makes it easier to debug and improve AI. Because we can observe the agent’s thoughts, we can (1) more easily diagnose why things are going wrong, making it easier to fix the problem, (2) steer the agent by correcting its thinking, or (3) prevent it from doing unsafe things it plans to do. Overall, by training agents $\textit{how to think}$ as well as behave, Thought Cloning creates safer, more powerful agents.

Praneeth Kacham, David Woodruff

We study lower bounds on adaptive sensing algorithms for recovering low rank matrices using linear measurements. Given an $n \times n$ matrix $A$, a general linear measurement $S(A)$, for an $n \times n$ matrix $S$, is just the inner product of $S$ and $A$, each treated as $n^2$-dimensional vectors. By performing as few linear measurements as possible on a rank-$r$ matrix $A$, we hope to construct a matrix $\hat{A}$ that satisfies $|A - \hat{A}|\_F^2 \le c |A|\_F^2$, for a small constant $c$. Here $|A|\_F$ denotes the Frobenius norm $(\sum_{i,j} A_{i,j}^2)^{1/2}$. It is commonly assumed that when measuring $A$ with $S$, the response is corrupted with an independent Gaussian random variable of mean $0$ and variance $\sigma^2$. Candès and Plan (IEEE Trans. Inform. Theory 2011) study non-adaptive algorithms for low rank matrix recovery using random linear measurements. They use the restricted isometry property (RIP) of Random Gaussian Matrices to give tractable algorithms to estimate $A$ from the measurements.At the edge of the noise level where recovery is information-theoretically feasible, it is known that their non-adaptive algorithms need to perform $\Omega(n^2)$ measurements, which amounts to reading the entire matrix. An important question is whether adaptivity helps in decreasing the overall number of measurements. While for the related problem of sparse recovery, adaptive algorithms have been extensively studied, as far as we are aware adaptive algorithms and lower bounds on them seem largely unexplored for matrix recovery. We show that any adaptive algorithm that uses $k$ linear measurements in each round and outputs an approximation as in (1) with probability $\ge 9/10$ must run for $t = \Omega(\log(n^2/k)/\log\log n)$ rounds. Our lower bound shows that any adaptive algorithm which uses $n^{2-\beta}$ ($\beta > 0$ is arbitrary constant) linear measurements in each round must run for $\Omega(\log n/\log\log n)$ rounds. Our techniques also readily extend to obtain lower bounds on adaptive algorithms for tensor recovery. Our hard distribution also allows us to give a measurement-vs-rounds trade-off for many sensing problems in numerical linear algebra, such as spectral norm low rank approximation, Frobenius norm low rank approximation, singular vector approximation, and more.

Applications/Language, Speech and Dialog

Chunting Zhou, Pengfei Liu, Puxin Xu, Srinivasan Iyer, Jiao Sun, Yuning Mao, Xuezhe Ma, Avia Efrat, Ping Yu, LILI YU 等

Large language models are trained in two stages: (1) unsupervised pretraining from raw text, to learn general-purpose representations, and (2) large scale instruction tuning and reinforcement learning, to better align to end tasks and user preferences. We measure the relative importance of these two stages by training LIMA, a 65B parameter LLaMa language model fine-tuned with the standard supervised loss on only 1,000 carefully curated prompts and responses, without any reinforcement learning or human preference modeling.LIMA demonstrates remarkably strong performance, learning to follow specific response formats from only a handful of examples in the training data, including complex queries that range from planning trip itineraries to speculating about alternate history.Moreover, the model tends to generalize well to unseen tasks that did not appear in the training data.In a controlled human study, responses from LIMA are either equivalent or strictly preferred to GPT-4 in 43\% of cases; this statistic is as high as 58\% when compared to Bard and 65\% versus DaVinci003, which was trained with human feedback.Taken together, these results strongly suggest that almost all knowledge in large language models is learned during pretraining, and only limited instruction tuning data is necessary to teach models to produce high quality output.

Theory/Reinforcement Learning and Planning

Wenzhuo Zhou

We study offline reinforcement learning (RL) which seeks to learn a good policy based on a fixed, pre-collected dataset. A fundamental challenge behind this task is the distributional shift due to the dataset lacking sufficient exploration, especially under function approximation. To tackle this issue, we propose a bi-level structured policy optimization algorithm that models a hierarchical interaction between the policy (upper-level) and the value function (lower-level). The lower level focuses on constructing a confidence set of value estimates that maintain sufficiently small weighted average Bellman errors, while controlling uncertainty arising from distribution mismatch. Subsequently, at the upper level, the policy aims to maximize a conservative value estimate from the confidence set formed at the lower level. This novel formulation preserves the maximum flexibility of the implicitly induced exploratory data distribution, enabling the power of model extrapolation. In practice, it can be solved through a computationally efficient, penalized adversarial estimation procedure. Our theoretical regret guarantees do not rely on any data-coverage and completeness-type assumptions, only requiring realizability. These guarantees also demonstrate that the learned policy represents the ``best effort'' among all policies, as no other policies can outperform it. We evaluate our model using a blend of synthetic, benchmark, and real-world datasets for offline RL, showing that it performs competitively with state-of-the-art methods.

Theory/Reinforcement Learning and Planning

Yuhao Wang, Enlu Zhou

We consider a robust reinforcement learning problem, where a learning agent learns from a simulated training environment. To account for the model mis-specification between this training environment and the true environment due to lack of data, we adopt a formulation of Bayesian risk MDP (BRMDP) with infinite horizon, which uses Bayesian posterior to estimate the transition model and impose a risk functional to account for the model uncertainty. Observations from the real environment that is out of the agent's control arrive periodically and are utilized by the agent to update the Bayesian posterior to reduce model uncertainty. We theoretically demonstrate that BRMDP balances the trade-off between robustness and conservativeness, and we further develop a multi-stage Bayesian risk-averse Q-learning algorithm to solve BRMDP with streaming observations from real environment. The proposed algorithm learns a risk-averse yet optimal policy that depends on the availability of real-world observations. We provide a theoretical guarantee of strong convergence for the proposed algorithm.

Theory/Reinforcement Learning and Planning

Zeyu Jia, Gene Li, Alexander Rakhlin, Ayush Sekhari, Nati Srebro

We study the problem of agnostic PAC reinforcement learning (RL): given a policy class $\Pi$, how many rounds of interaction with an unknown MDP (with a potentially large state and action space) are required to learn an $\epsilon$-suboptimal policy with respect to \(\Pi\)? Towards that end, we introduce a new complexity measure, called the \emph{spanning capacity}, that depends solely on the set \(\Pi\) and is independent of the MDP dynamics. With a generative model, we show that the spanning capacity characterizes PAC learnability for every policy class $\Pi$. However, for online RL, the situation is more subtle. We show there exists a policy class $\Pi$ with a bounded spanning capacity that requires a superpolynomial number of samples to learn. This reveals a surprising separation for agnostic learnability between generative access and online access models (as well as between deterministic/stochastic MDPs under online access). On the positive side, we identify an additional \emph{sunflower} structure which in conjunction with bounded spanning capacity enables statistically efficient online RL via a new algorithm called POPLER, which takes inspiration from classical importance sampling methods as well as recent developments for reachable-state identification and policy evaluation in reward-free exploration.

Theory/Reinforcement Learning and Planning

Yuan Cheng, Jing Yang, Yingbin Liang

Reinforcement learning (RL) under changing environment models many real-world applications via nonstationary Markov Decision Processes (MDPs), and hence gains considerable interest. However, theoretical studies on nonstationary MDPs in the literature have mainly focused on tabular and linear (mixture) MDPs, which do not capture the nature of unknown representation in deep RL. In this paper, we make the first effort to investigate nonstationary RL under episodic low-rank MDPs, where both transition kernels and rewards may vary over time, and the low-rank model contains unknown representation in addition to the linear state embedding function. We first propose a parameter-dependent policy optimization algorithm called PORTAL,and further improve PORTAL to its parameter-free version of Ada-PORTAL, which is able to tune its hyper-parameters adaptively without any prior knowledge of nonstationarity. For both algorithms, we provide upper bounds on the average dynamic suboptimality gap, which show that as long as the nonstationarity is not significantly large, PORTAL and Ada-PORTAL are sample-efficient and can achieve arbitrarily small average dynamic suboptimality gap with polynomial sample complexity.

Theory/Reinforcement Learning and Planning

Udaya Ghai, Arushi Gupta, Wenhan Xia, Karan Singh, Elad Hazan

We investigate robust model-free reinforcement learning algorithms designed for environments that may be dynamic or even adversarial. Traditional state-based policies often struggle to accommodate the challenges imposed by the presence of unmodeled disturbances in such settings. Moreover, optimizing linear state-based policies pose an obstacle for efficient optimization, leading to nonconvex objectives, even in benign environments like linear dynamical systems.Drawing inspiration from recent advancements in model-based control, we intro- duce a novel class of policies centered on disturbance signals. We define several categories of these signals, which we term pseudo-disturbances, and develop corresponding policy classes based on them. We provide efficient and practical algorithms for optimizing these policies.Next, we examine the task of online adaptation of reinforcement learning agents in the face of adversarial disturbances. Our methods seamlessly integrate with any black-box model-free approach, yielding provable regret guarantees when dealing with linear dynamics. These regret guarantees unconditionally improve the best-known results for bandit linear control in having no dependence on the state-space dimension. We evaluate our method over various standard RL benchmarks and demonstrate improved robustness.

Reinforcement Learning/Planning

Pulkit Verma, Rushang Karia, Siddharth Srivastava

It is essential for users to understand what their AI systems can and can't do in order to use them safely. However, the problem of enabling users to assess AI systems with sequential decision-making (SDM) capabilities is relatively understudied. This paper presents a new approach for modeling the capabilities of black-box AI systems that can plan and act, along with the possible effects and requirements for executing those capabilities in stochastic settings. We present an active-learning approach that can effectively interact with a black-box SDM system and learn an interpretable probabilistic model describing its capabilities. Theoretical analysis of the approach identifies the conditions under which the learning process is guaranteed to converge to the correct model of the agent; empirical evaluations on different agents and simulated scenarios show that this approach is few-shot generalizable and can effectively describe the capabilities of arbitrary black-box SDM agents in a sample-efficient manner.

Reinforcement Learning/Planning

Zihao Wang, Shaofei Cai, Guanzhou Chen, Anji Liu, Xiaojian (Shawn) Ma, Yitao Liang

In this paper, we study the problem of planning in Minecraft, a popular, democratized yet challenging open-ended environment for developing multi-task embodied agents. We've found two primary challenges of empowering such agents with planning: 1) planning in an open-ended world like Minecraft requires precise and multi-step reasoning due to the long-term nature of the tasks, and 2) as vanilla planners do not consider the achievability of the current agent when ordering parallel sub-goals within a complicated plan, the resulting plan could be inefficient. To this end, we propose ``$\underline{D}$escribe, $\underline{E}$xplain, $\underline{P}$lan and $\underline{S}$elect'' ($\textbf{DEPS}$), an interactive planning approach based on Large Language Models (LLMs). Our approach helps with better error correction from the feedback during the long-haul planning, while also bringing the sense of proximity via goal $\textbf{Selector}$, a learnable module that ranks parallel sub-goals based on the estimated steps of completion and improves the original plan accordingly. Our experiments mark the milestone of the first zero-shot multi-task agent that can robustly accomplish 70+ Minecraft tasks and nearly double the overall performances. Further testing reveals our method's general effectiveness in popularly adopted non-open-ended domains as well (i.e., ALFWorld and tabletop manipulation). The ablation and exploratory studies detail how our design beats the counterparts and provide a promising update on the $\texttt{ObtainDiamond}$ grand challenge with our approach.

Deep Learning/Generative Models and Autoencoders

Nikita Gushchin, Alexander Kolesov, Alexander Korotin, Dmitry Vetrov, Evgeny Burnaev

We propose a novel neural algorithm for the fundamental problem of computing the entropic optimal transport (EOT) plan between probability distributions which are accessible by samples. Our algorithm is based on the saddle point reformulation of the dynamic version of EOT which is known as the Schrödinger Bridge problem. In contrast to the prior methods for large-scale EOT, our algorithm is end-to-end and consists of a single learning step, has fast inference procedure, and allows handling small values of the entropy regularization coefficient which is of particular importance in some applied problems. Empirically, we show the performance of the method on several large-scale EOT tasks. The code for the ENOT solver can be found at https://github.com/ngushchin/EntropicNeuralOptimalTransport

Reinforcement Learning/Planning

Xiao Zang, Miao Yin, Jinqi Xiao, Saman Zonouz, Bo Yuan

Motion planning, which aims to find a high-quality collision-free path in the configuration space, is a fundamental task in robotic systems. Recently, learning-based motion planners, especially the graph neural network-powered, have shown promising planning performance. However, though the state-of-the-art GNN planner can efficiently extract and learn graph information, its inherent mechanism is not well suited for graph search process, hindering its further performance improvement. To address this challenge and fully unleash the potential of GNN in motion planning, this paper proposes GraphMP, a neural motion planner for both low and high-dimensional planning tasks. With the customized model architecture and training mechanism design, GraphMP can simultaneously perform efficient graph pattern extraction and graph search processing, leading to strong planning performance. Experiments on a variety of environments, ranging from 2D Maze to 14D dual KUKA robotic arm, show that our proposed GraphMP achieves significant improvement on path quality and planning speed over the state-of-the-art learning-based and classical planners; while preserving the competitive success rate.

Theory/Reinforcement Learning and Planning

Yunchang Yang, Han Zhong, Tianhao Wu, Bin Liu, Liwei Wang, Simon Du

We study stochastic delayed feedback in general single-agent and multi-agent sequential decision making, which includes bandits, single-agent Markov decision processes (MDPs), and Markov games (MGs). We propose a novel reduction-based framework, which turns any multi-batched algorithm for sequential decision making with instantaneous feedback into a sample-efficient algorithm that can handle stochastic delays in sequential decision making. By plugging different multi-batched algorithms into our framework, we provide several examples demonstrating that our framework not only matches or improves existing results for bandits, tabular MDPs, and tabular MGs, but also provides the first line of studies on delays in sequential decision making with function approximation. In summary, we provide a complete set of sharp results for single-agent and multi-agent sequential decision making with delayed feedback.

Deep Learning/Generative Models and Autoencoders

Zhonghang Li, Lianghao Xia, Yong Xu, Chao Huang

In recent years, there has been a rapid development of spatio-temporal prediction techniques in response to the increasing demands of traffic management and travel planning. While advanced end-to-end models have achieved notable success in improving predictive performance, their integration and expansion pose significant challenges. This work aims to address these challenges by introducing a spatio-temporal pre-training framework that seamlessly integrates with downstream baselines and enhances their performance. The framework is built upon two key designs: (i) We propose a spatio-temporal mask autoencoder as a pre-training model for learning spatio-temporal dependencies. The model incorporates customized parameter learners and hierarchical spatial pattern encoding networks. These modules are specifically designed to capture spatio-temporal customized representations and intra- and inter-cluster region semantic relationships, which have often been neglected in existing approaches. (ii) We introduce an adaptive mask strategy as part of the pre-training mechanism. This strategy guides the mask autoencoder in learning robust spatio-temporal representations and facilitates the modeling of different relationships, ranging from intra-cluster to inter-cluster, in an easy-to-hard training manner. Extensive experiments conducted on representative benchmarks demonstrate the effectiveness of our proposed method. We have made our model implementation publicly available at https://github.com/HKUDS/GPT-ST.

Arnav Kumar Jain, Lucas Lehnert, Irina Rish, Glen Berseth

Animals have a developed ability to explore that aids them in important tasks such as locating food, exploring for shelter, and finding misplaced items. These exploration skills necessarily track where they have been so that they can plan for finding items with relative efficiency. Contemporary exploration algorithms often learn a less efficient exploration strategy because they either condition only on the current state or simply rely on making random open-loop exploratory moves. In this work, we propose $\eta\psi$-Learning, a method to learn efficient exploratory policies by conditioning on past episodic experience to make the next exploratory move. Specifically, $\eta\psi$-Learning learns an exploration policy that maximizes the entropy of the state visitation distribution of a single trajectory. Furthermore, we demonstrate how variants of the predecessor representation and successor representations can be combined to predict the state visitation entropy. Our experiments demonstrate the efficacy of $\eta\psi$-Learning to strategically explore the environment and maximize the state coverage with limited samples.

Theory/Reinforcement Learning and Planning

Xiaoyan Hu, Ho-fung Leung

The options framework yields empirical success in long-horizon planning problems of reinforcement learning (RL). Recent works show that options help improve the sample efficiency in online RL. However, these results are no longer applicable to scenarios where exploring the environment online is risky, e.g., automated driving and healthcare. In this paper, we provide the first analysis of the sample complexity for offline RL with options, where the agent learns from a dataset without further interaction with the environment. We derive a novel information-theoretic lower bound, which generalizes the one for offline learning with actions. We propose the PEssimistic Value Iteration for Learning with Options (PEVIO) algorithm and establish near-optimal suboptimality bounds for two popular data-collection procedures, where the first one collects state-option transitions and the second one collects state-action transitions. We show that compared to offline RL with actions, using options not only enjoys a faster finite-time convergence rate (to the optimal value) but also attains a better performance when either the options are carefully designed or the offline data is limited. Based on these results, we analyze the pros and cons of the data-collection procedures.