Digital human recommendation system has been developed to help customers find their favorite products and is playing an active role in various recommendation contexts. How to timely catch and learn the dynamics of the preferences of the customers, while meeting their exact requirements, becomes crucial in the digital human recommendation domain. We design a novel practical digital human interactive recommendation agent framework based on Reinforcement Learning(RL) to improve the efficiency of the interactive recommendation decision-making by leveraging both the digital human features and the superior flexibility of RL. Our proposed framework learns through real-time interactions between the digital human and customers dynamically through the state-of-the-art RL algorithms, combined with multi-modal embedding and graph embedding, to improve the accuracy of personalization and thus enable the digital human agent to timely catch the attention of the customer. Experiments on real business data demonstrate that our framework can provide better personalized customer engagement and better customer experiences.

Skill-based reinforcement learning (RL) has emerged as a promising strategy to leverage prior knowledge for accelerated robot learning. Skills are typically extracted from expert demonstrations and are embedded into a latent space from which they can be sampled as actions by a high-level RL agent. However, this skill space is expansive, and not all skills are relevant for a given robot state, making exploration difficult. Furthermore, the downstream RL agent is limited to learning structurally similar tasks to those used to construct the skill space. We firstly propose accelerating exploration in the skill space using state-conditioned generative models to directly bias the high-level agent towards only sampling skills relevant to a given state based on prior experience. Next, we propose a low-level residual policy for fine-grained skill adaptation enabling downstream RL agents to adapt to unseen task variations. Finally, we validate our approach across four challenging manipulation tasks that differ from those used to build the skill space, demonstrating our ability to learn across task variations while significantly accelerating exploration, outperforming prior works. Code and videos are available on our project website: https://krishanrana.github.io/reskill.

This paper is concerned with constructing a confidence interval for a target policy's value offline based on a pre-collected observational data in infinite horizon settings. Most of the existing works assume no unmeasured variables exist that confound the observed actions. This assumption, however, is likely to be violated in real applications such as healthcare and technological industries. In this paper, we show that with some auxiliary variables that mediate the effect of actions on the system dynamics, the target policy's value is identifiable in a confounded Markov decision process. Based on this result, we develop an efficient off-policy value estimator that is robust to potential model misspecification and provide rigorous uncertainty quantification. Our method is justified by theoretical results, simulated and real datasets obtained from ridesharing companies. A Python implementation of the proposed procedure is available at https://github.com/Mamba413/cope.

Program synthesis or code generation aims to generate a program that satisfies a problem specification. Recent approaches using large-scale pretrained language models (LMs) have shown promising results, yet they have some critical limitations. In particular, they often follow a standard supervised fine-tuning procedure to train a code generation model only from the pairs of natural-language problem descriptions and ground-truth programs. Such paradigm largely ignores some important but potentially useful signals in the problem specification such as unit tests, which thus often results in poor performance when solving complex unseen coding tasks. To address the limitations, we propose "CodeRL", a new framework for program synthesis tasks through pretrained LMs and deep reinforcement learning (RL). Specifically, during training, we treat the code-generating LM as an actor network, and introduce a critic network that is trained to predict the functional correctness of generated programs and provide dense feedback signals to the actor. During inference, we introduce a new generation procedure with a critical sampling strategy that allows a model to automatically regenerate programs based on feedback from example unit tests and critic scores. For the model backbones, we extended the encoder-decoder architecture of CodeT5 with enhanced learning objectives, larger model sizes, and better pretraining data. Our method not only achieves new SOTA results on the challenging APPS benchmark, but also shows strong zero-shot transfer capability with new SOTA results on the simpler MBPP benchmark.

Exploration with sparse rewards remains a challenging research problem in reinforcement learning (RL). Especially for sequential object manipulation tasks, the RL agent always receives negative rewards until completing all sub-tasks, which results in low exploration efficiency. To solve these tasks efficiently, we propose a novel self-guided continual RL framework, RelayHER (RHER). RHER first decomposes a sequential task into new sub-tasks with increasing complexity and ensures that the simplest sub-task can be learned quickly by utilizing Hindsight Experience Replay (HER). Secondly, we design a multi-goal & multi-task network to learn these sub-tasks simultaneously. Finally, we propose a Self-Guided Exploration Strategy (SGES). With SGES, the learned sub-task policy will guide the agent to the states that are helpful to learn more complex sub-task with HER. By this self-guided exploration and relay policy learning, RHER can solve these sequential tasks efficiently stage by stage. The experimental results show that RHER significantly outperforms vanilla-HER in sample-efficiency on five singleobject and five complex multi-object manipulation tasks (e.g., Push, Insert, ObstaclePush, Stack, TStack, etc.). The proposed RHER has also been applied to learn a contact-rich push task on a physical robot from scratch, and the success rate reached 10/10 with only 250 episodes.

Bimanual activities like coffee stirring, which require coordination of dual arms, are common in daily life and intractable to learn by robots. Adopting reinforcement learning to learn these tasks is a promising topic since it enables the robot to explore how dual arms coordinate together to accomplish the same task. However, this field has two main challenges: coordination mechanism and long-horizon task decomposition. Therefore, we propose the Mixline method to learn sub-tasks separately via the online algorithm and then compose them together based on the generated data through the offline algorithm. We constructed a learning environment based on the GPU-accelerated Isaac Gym. In our work, the bimanual robot successfully learned to grasp, hold and lift the spoon and cup, insert them together and stir the coffee. The proposed method has the potential to be extended to other long-horizon bimanual tasks.

In offline reinforcement learning (RL), a learner leverages prior logged data to learn a good policy without interacting with the environment. A major challenge in applying such methods in practice is the lack of both theoretically principled and practical tools for model selection and evaluation. To address this, we study the problem of model selection in offline RL with value function approximation. The learner is given a nested sequence of model classes to minimize squared Bellman error and must select among these to achieve a balance between approximation and estimation error of the classes. We propose the first model selection algorithm for offline RL that achieves minimax rate-optimal oracle inequalities up to logarithmic factors. The algorithm, ModBE, takes as input a collection of candidate model classes and a generic base offline RL algorithm. By successively eliminating model classes using a novel one-sided generalization test, ModBE returns a policy with regret scaling with the complexity of the minimally complete model class. In addition to its theoretical guarantees, it is conceptually simple and computationally efficient, amounting to solving a series of square loss regression problems and then comparing relative square loss between classes. We conclude with several numerical simulations showing it is capable of reliably selecting a good model class.

Model-based reinforcement learning (RL) methods are appealing in the offline setting because they allow an agent to reason about the consequences of actions without interacting with the environment. Prior methods learn a 1-step dynamics model, which predicts the next state given the current state and action. These models do not immediately tell the agent which actions to take, but must be integrated into a larger RL framework. Can we model the environment dynamics in a different way, such that the learned model does directly indicate the value of each action? In this paper, we propose Contrastive Value Learning (CVL), which learns an implicit, multi-step model of the environment dynamics. This model can be learned without access to reward functions, but nonetheless can be used to directly estimate the value of each action, without requiring any TD learning. Because this model represents the multi-step transitions implicitly, it avoids having to predict high-dimensional observations and thus scales to high-dimensional tasks. Our experiments demonstrate that CVL outperforms prior offline RL methods on complex continuous control benchmarks.

Reinforcement Learning (RL)-based control system has received considerable attention in recent decades. However, in many real-world problems, such as Batch Process Control, the environment is uncertain, which requires expensive interaction to acquire the state and reward values. In this paper, we present a cost-efficient framework, such that the RL model can evolve for itself in a Virtual Space using the predictive models with only historical data. The proposed framework enables a step-by-step RL model to predict the future state and select optimal actions for long-sight decisions. The main focuses are summarized as: 1) how to balance the long-sight and short-sight rewards with an optimal strategy; 2) how to make the virtual model interacting with real environment to converge to a final learning policy. Under the experimental settings of Fed-Batch Process, our method consistently outperforms the existing state-of-the-art methods.

In a modern power system with an increasing proportion of renewable energy, wind power prediction is crucial to the arrangement of power grid dispatching plans due to the volatility of wind power. However, traditional centralized forecasting methods raise concerns regarding data privacy-preserving and data islands problem. To handle the data privacy and openness, we propose a forecasting scheme that combines federated learning and deep reinforcement learning (DRL) for ultra-short-term wind power forecasting, called federated deep reinforcement learning (FedDRL). Firstly, this paper uses the deep deterministic policy gradient (DDPG) algorithm as the basic forecasting model to improve prediction accuracy. Secondly, we integrate the DDPG forecasting model into the framework of federated learning. The designed FedDRL can obtain an accurate prediction model in a decentralized way by sharing model parameters instead of sharing private data which can avoid sensitive privacy issues. The simulation results show that the proposed FedDRL outperforms the traditional prediction methods in terms of forecasting accuracy. More importantly, while ensuring the forecasting performance, FedDRL can effectively protect the data privacy and relieve the communication pressure compared with the traditional centralized forecasting method. In addition, a simulation with different federated learning parameters is conducted to confirm the robustness of the proposed scheme.