Offline reinforcement learning, which aims at optimizing sequential decision-making strategies with historical data, has been extensively applied in real-life applications. State-Of-The-Art algorithms usually leverage powerful function approximators (e.g. neural networks) to alleviate the sample complexity hurdle for better empirical performances. Despite the successes, a more systematic understanding of the statistical complexity for function approximation remains lacking. Towards bridging the gap, we take a step by considering offline reinforcement learning with differentiable function class approximation (DFA). This function class naturally incorporates a wide range of models with nonlinear/nonconvex structures. Most importantly, we show offline RL with differentiable function approximation is provably efficient by analyzing the pessimistic fitted Q-learning (PFQL) algorithm, and our results provide the theoretical basis for understanding a variety of practical heuristics that rely on Fitted Q-Iteration style design. In addition, we further improve our guarantee with a tighter instance-dependent characterization. We hope our work could draw interest in studying reinforcement learning with differentiable function approximation beyond the scope of current research.

We study the problem of imitating object interactions from Internet videos. This requires understanding the hand-object interactions in 4D, spatially in 3D and over time, which is challenging due to mutual hand-object occlusions. In this paper we make two main contributions: (1) a novel reconstruction technique RHOV (Reconstructing Hands and Objects from Videos), which reconstructs 4D trajectories of both the hand and the object using 2D image cues and temporal smoothness constraints; (2) a system for imitating object interactions in a physics simulator with reinforcement learning. We apply our reconstruction technique to 100 challenging Internet videos. We further show that we can successfully imitate a range of different object interactions in a physics simulator. Our object-centric approach is not limited to human-like end-effectors and can learn to imitate object interactions using different embodiments, like a robotic arm with a parallel jaw gripper.

Deep reinforcement learning (DRL) breaks through the bottlenecks of traditional reinforcement learning (RL) with the help of the perception capability of deep learning and has been widely applied in real-world problems.While model-free RL, as a class of efficient DRL methods, performs the learning of state representations simultaneously with policy learning in an end-to-end manner when facing large-scale continuous state and action spaces. However, training such a large policy model requires a large number of trajectory samples and training time. On the other hand, the learned policy often fails to generalize to large-scale action spaces, especially for the continuous action spaces. To address this issue, in this paper we propose an efficient policy learning method in latent state and action spaces. More specifically, we extend the idea of state representations to action representations for better policy generalization capability. Meanwhile, we divide the whole learning task into learning with the large-scale representation models in an unsupervised manner and learning with the small-scale policy model in the RL manner.The small policy model facilitates policy learning, while not sacrificing generalization and expressiveness via the large representation model. Finally,the effectiveness of the proposed method is demonstrated by MountainCar,CarRacing and Cheetah experiments.

Unmanned aerial vehicles (UAVs) have the potential to establish flexible and reliable emergency networks in disaster sites when terrestrial communication infrastructures go down. Nevertheless, potential security threats may occur on UAVs during data transmissions due to the untrusted environment and open-access UAV networks. Moreover, UAVs typically have limited battery and computation capacity, making them unaffordable for heavy security provisioning operations when performing complicated rescue tasks. In this paper, we develop RescueChain, a secure and efficient information sharing scheme for UAV-assisted disaster rescue. Specifically, we first implement a lightweight blockchain-based framework to safeguard data sharing under disasters and immutably trace misbehaving entities. A reputation-based consensus protocol is devised to adapt the weakly connected environment with improved consensus efficiency and promoted UAVs' honest behaviors. Furthermore, we introduce a novel vehicular fog computing (VFC)-based off-chain mechanism by leveraging ground vehicles as moving fog nodes to offload UAVs' heavy data processing and storage tasks. To offload computational tasks from the UAVs to ground vehicles having idle computing resources, an optimal allocation strategy is developed by choosing payoffs that achieve equilibrium in a Stackelberg game formulation of the allocation problem. For lack of sufficient knowledge on network model parameters and users' private cost parameters in practical environment, we also design a two-tier deep reinforcement learning-based algorithm to seek the optimal payment and resource strategies of UAVs and vehicles with improved learning efficiency. Simulation results show that RescueChain can effectively accelerate consensus process, improve offloading efficiency, reduce energy consumption, and enhance user payoffs.

Tactile sensors have been introduced to a wide range of robotic tasks such as robot manipulation to mimic the sense of human touch. However, there has only been a few works that integrate tactile sensing into robot navigation. This paper describes a navigation system which allows robots to operate in crowded human-dense environments and behave with socially acceptable reactions by utilizing semantic and force information collected by embedded tactile sensors, RGB-D camera and LiDAR. Compliance control is implemented based on artificial potential fields considering not only laser scan but also force reading from tactile sensors which promises a fast and reliable response to any possible collision. In contrast to cameras, LiDAR and other non-contact sensors, tactile sensors can directly interact with humans and can be used to accept social cues akin to natural human behavior under the same situation. Furthermore, leveraging semantic segmentation from vision module, the robot is able to identify and, therefore assign varying social cost to different groups of humans enabling for socially conscious path planning. At the end of this paper, the proposed control strategy was validated successfully by testing several scenarios on an omni-directional robot in real world.

Reinforcement learning (RL) is currently used in various real-life applications. RL-based solutions have the potential to generically address problems, including the ones that are difficult to solve with heuristics and meta-heuristics and, in addition, the set of problems and issues where some intelligent or cognitive approach is required. However, reinforcement learning agents require a not straightforward design and have important design issues. RL agent design issues include the target problem modeling, state-space explosion, the training process, and agent efficiency. Research currently addresses these issues aiming to foster RL dissemination. A BAM model, in summary, allocates and shares resources with users. There are three basic BAM models and several hybrids that differ in how they allocate and share resources among users. This paper addresses the issue of an RL agent design and efficiency. The RL agent's objective is to allocate and share resources among users. The paper investigates how a BAM model can contribute to the RL agent design and efficiency. The AllocTC-Sharing (ATCS) model is analytically described and simulated to evaluate how it mimics the RL agent operation and how the ATCS can offload computational tasks from the RL agent. The essential argument researched is whether algorithms integrated with the RL agent design and operation have the potential to facilitate agent design and optimize its execution. The ATCS analytical model and simulation presented demonstrate that a BAM model offloads agent tasks and assists the agent's design and optimization.

This paper introduces a simple efficient learning algorithms for general sequential decision making. The algorithm combines Optimism for exploration with Maximum Likelihood Estimation for model estimation, which is thus named OMLE. We prove that OMLE learns the near-optimal policies of an enormously rich class of sequential decision making problems in a polynomial number of samples. This rich class includes not only a majority of known tractable model-based Reinforcement Learning (RL) problems (such as tabular MDPs, factored MDPs, low witness rank problems, tabular weakly-revealing/observable POMDPs and multi-step decodable POMDPs), but also many new challenging RL problems especially in the partially observable setting that were not previously known to be tractable. Notably, the new problems addressed by this paper include (1) observable POMDPs with continuous observation and function approximation, where we achieve the first sample complexity that is completely independent of the size of observation space; (2) well-conditioned low-rank sequential decision making problems (also known as Predictive State Representations (PSRs)), which include and generalize all known tractable POMDP examples under a more intrinsic representation; (3) general sequential decision making problems under SAIL condition, which unifies our existing understandings of model-based RL in both fully observable and partially observable settings. SAIL condition is identified by this paper, which can be viewed as a natural generalization of Bellman/witness rank to address partial observability. This paper also presents a reward-free variant of OMLE algorithm, which learns approximate dynamic models that enable the computation of near-optimal policies for all reward functions simultaneously.

Natural and formal languages provide an effective mechanism for humans to specify instructions and reward functions. We investigate how to generate policies via RL when reward functions are specified in a symbolic language captured by Reward Machines, an increasingly popular automaton-inspired structure. We are interested in the case where the mapping of environment state to a symbolic (here, Reward Machine) vocabulary -- commonly known as the labelling function -- is uncertain from the perspective of the agent. We formulate the problem of policy learning in Reward Machines with noisy symbolic abstractions as a special class of POMDP optimization problem, and investigate several methods to address the problem, building on existing and new techniques, the latter focused on predicting Reward Machine state, rather than on grounding of individual symbols. We analyze these methods and evaluate them experimentally under varying degrees of uncertainty in the correct interpretation of the symbolic vocabulary. We verify the strength of our approach and the limitation of existing methods via an empirical investigation on both illustrative, toy domains and partially observable, deep RL domains.

Transfer of recent advances in deep reinforcement learning to real-world applications is hindered by high data demands and thus low efficiency and scalability. Through independent improvements of components such as replay buffers or more stable learning algorithms, and through massively distributed systems, training time could be reduced from several days to several hours for standard benchmark tasks. However, while rewards in simulated environments are well-defined and easy to compute, reward evaluation becomes the bottleneck in many real-world environments, e.g., in molecular optimization tasks, where computationally demanding simulations or even experiments are required to evaluate states and to quantify rewards. Therefore, training might become prohibitively expensive without an extensive amount of computational resources and time. We propose to alleviate this problem by replacing costly ground-truth rewards with rewards modeled by neural networks, counteracting non-stationarity of state and reward distributions during training with an active learning component. We demonstrate that using our proposed ACRL method (actively learning costly rewards for reinforcement learning), it is possible to train agents in complex real-world environments orders of magnitudes faster. By enabling the application of reinforcement learning methods to new domains, we show that we can find interesting and non-trivial solutions to real-world optimization problems in chemistry, materials science and engineering.

The latent world model provides a promising way to learn policies in a compact latent space for tasks with high-dimensional observations, however, its generalization across diverse environments with unseen dynamics remains challenging. Although the recurrent structure utilized in current advances helps to capture local dynamics, modeling only state transitions without an explicit understanding of environmental context limits the generalization ability of the dynamics model. To address this issue, we propose a Prototypical Context-Aware Dynamics (ProtoCAD) model, which captures the local dynamics by time consistent latent context and enables dynamics generalization in high-dimensional control tasks. ProtoCAD extracts useful contextual information with the help of the prototypes clustered over batch and benefits model-based RL in two folds: 1) It utilizes a temporally consistent prototypical regularizer that encourages the prototype assignments produced for different time parts of the same latent trajectory to be temporally consistent instead of comparing the features; 2) A context representation is designed which combines both the projection embedding of latent states and aggregated prototypes and can significantly improve the dynamics generalization ability. Extensive experiments show that ProtoCAD surpasses existing methods in terms of dynamics generalization. Compared with the recurrent-based model RSSM, ProtoCAD delivers 13.2% and 26.7% better mean and median performance across all dynamics generalization tasks. Latent world models (Ha & Schmidhuber, 2018) summarize an agent's experience from highdimensional observations to facilitate learning complex behaviors in a compact latent space. Current advances (Hafner et al., 2019; 2020; Deng et al., 2022) leverage Recurrent Neural Networks (RNNs) to extract historical information from high-dimensional observations as compact latent representations and enable imagination in the latent space. However, modeling only latent state transitions without an explicit understanding of the environmental context characteristics limits the dynamics generalization ability of the world model. Since the changes in dynamics are not observable and can only be inferred from the observation sequence, for tasks with high-dimensional sensor inputs, dynamics generalization remains challenging.