To achieve the ambitious goals of artificial intelligence, reinforcement learning must include planning with a model of the world that is abstract in state and time. Deep learning has made progress with state abstraction, but temporal abstraction has rarely been used, despite extensively developed theory based on the options framework. One reason for this is that the space of possible options is immense, and the methods previously proposed for option discovery do not take into account how the option models will be used in planning. Options are typically discovered by posing subsidiary tasks, such as reaching a bottleneck state or maximizing the cumulative sum of a sensory signal other than reward. Each subtask is solved to produce an option, and then a model of the option is learned and made available to the planning process. In most previous work, the subtasks ignore the reward on the original problem, whereas we propose subtasks that use the original reward plus a bonus based on a feature of the state at the time the option terminates. We show that option models obtained from such reward-respecting subtasks are much more likely to be useful in planning than eigenoptions, shortest path options based on bottleneck states, or reward-respecting options generated by the option-critic. Reward respecting subtasks strongly constrain the space of options and thereby also provide a partial solution to the problem of option discovery. Finally, we show how values, policies, options, and models can all be learned online and off-policy using standard algorithms and general value functions.
An inverse reinforcement learning (IRL) agent learns to act intelligently by observing expert demonstrations and learning the expert's underlying reward function. Although learning the reward functions from demonstrations has achieved great success in various tasks, several other challenges are mostly ignored. Firstly, existing IRL methods try to learn the reward function from scratch without relying on any prior knowledge. Secondly, traditional IRL methods assume the reward functions are homogeneous across all the demonstrations. Some existing IRL methods managed to extend to the heterogeneou…
Although Deep Reinforcement Learning (DRL) has been popular in many disciplines including robotics, state-of-the-art DRL algorithms still struggle to learn long-horizon, multi-step and sparse reward tasks, such as stacking several blocks given only a task-completion reward signal. To improve learning efficiency for such tasks, this paper proposes a DRL exploration technique, termed A^2, which integrates two components inspired by human experiences: Abstract demonstrations and Adaptive exploration. A^2 starts by decomposing a complex task into subtasks, and then provides the correct orders of s…
Beijing University of Posts and Telecommunications（北京邮电大学）；Commonwealth Scientific and Industrial Research Organisation (CSIRO)（澳大利亚联邦科学与工业研究组织）；University of Technology Sydney（悉尼科技大学）
This paper presents a novel and effective deep reinforcement learning (DRL)-based approach to addressing joint resource management (JRM) in a practical multi-carrier non-orthogonal multiple access (MC-NOMA) system, where hardware sensitivity and imperfect successive interference cancellation (SIC) are considered. We first formulate the JRM problem to maximize the weighted-sum system throughput. Then, the JRM problem is decoupled into two iterative subtasks: subcarrier assignment (SA, including user grouping) and power allocation (PA). Each subtask is a sequential decision process. Invoking a d…
University of Michigan（密歇根大学）；DeepMind（深度思考）；Google Brain（谷歌大脑）
We introduce a new RL problem where the agent is required to generalize to a previously-unseen environment characterized by a subtask graph which describes a set of subtasks and their dependencies. Unlike existing hierarchical multitask RL approaches that explicitly describe what the agent should do at a high level, our problem only describes properties of subtasks and relationships among them, which requires the agent to perform complex reasoning to find the optimal subtask to execute. To solve this problem, we propose a neural subtask graph solver (NSGS) which encodes the subtask graph using…
We propose and address a novel few-shot RL problem, where a task is characterized by a subtask graph which describes a set of subtasks and their dependencies that are unknown to the agent. The agent needs to quickly adapt to the task over few episodes during adaptation phase to maximize the return in the test phase. Instead of directly learning a meta-policy, we develop a Meta-learner with Subtask Graph Inference(MSGI), which infers the latent parameter of the task by interacting with the environment and maximizes the return given the latent parameter. To facilitate learning, we adopt an intri…
Beijing University of Posts and Telecommunications（北京邮电大学）；SUTD（新加坡科技设计大学）；Commonwealth Scientific and Industrial Research Organisation (CSIRO)（联邦科学与工业研究组织（CSIRO））；NTU（南洋理工大学）
This paper proposes an effective and novel multiagent deep reinforcement learning (MADRL)-based method for solving the joint virtual network function (VNF) placement and routing (P&R), where multiple service requests with differentiated demands are delivered at the same time. The differentiated demands of the service requests are reflected by their delay- and cost-sensitive factors. We first construct a VNF P&R problem to jointly minimize a weighted sum of service delay and resource consumption cost, which is NP-complete. Then, the joint VNF P&R problem is decoupled into two iterative subtasks…
Humans decompose novel complex tasks into simpler ones to exploit previously learned skills. Analogously, hierarchical reinforcement learning seeks to leverage lower-level policies for simple tasks to solve complex ones. However, because each lower-level policy induces a different distribution of states, transitioning from one lower-level policy to another may fail due to an unexpected starting state. We introduce transition policies that smoothly connect lower-level policies by producing a distribution of states and actions that matches what is expected by the next policy. Training transition…
Sparse-reward domains are challenging for reinforcement learning algorithms since significant exploration is needed before encountering reward for the first time. Hierarchical reinforcement learning can facilitate exploration by reducing the number of decisions necessary before obtaining a reward. In this paper, we present a novel hierarchical reinforcement learning framework based on the compression of an invariant state space that is common to a range of tasks. The algorithm introduces subtasks which consist of moving between the state partitions induced by the compression. Results indicate …
We describe a framework for multitask deep reinforcement learning guided by policy sketches. Sketches annotate tasks with sequences of named subtasks, providing information about high-level structural relationships among tasks but not how to implement them---specifically not providing the detailed guidance used by much previous work on learning policy abstractions for RL (e.g. intermediate rewards, subtask completion signals, or intrinsic motivations). To learn from sketches, we present a model that associates every subtask with a modular subpolicy, and jointly maximizes reward over full task-…
Conventional video summarization approaches based on reinforcement learning have the problem that the reward can only be received after the whole summary is generated. Such kind of reward is sparse and it makes reinforcement learning hard to converge. Another problem is that labelling each frame is tedious and costly, which usually prohibits the construction of large-scale datasets. To solve these problems, we propose a weakly supervised hierarchical reinforcement learning framework, which decomposes the whole task into several subtasks to enhance the summarization quality. This framework cons…
University of Maryland, Baltimore County（马里兰大学巴尔的摩县分校）；Carnegie Mellon University（卡内基梅隆大学）；Georgia Institute of Technology（佐治亚理工学院）；University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校）；Simmons University（西蒙斯大学）
We introduce an algorithm for model-based hierarchical reinforcement learning to acquire self-contained transition and reward models suitable for probabilistic planning at multiple levels of abstraction. We call this framework Planning with Abstract Learned Models (PALM). By representing subtasks symbolically using a new formal structure, the lifted abstract Markov decision process (L-AMDP), PALM learns models that are independent and modular. Through our experiments, we show how PALM integrates planning and execution, facilitating a rapid and efficient learning of abstract, hierarchical model…
University of Michigan（密歇根大学）；Google Brain（谷歌大脑）；Microsoft Research（微软研究院）
As a step towards developing zero-shot task generalization capabilities in reinforcement learning (RL), we introduce a new RL problem where the agent should learn to execute sequences of instructions after learning useful skills that solve subtasks. In this problem, we consider two types of generalizations: to previously unseen instructions and to longer sequences of instructions. For generalization over unseen instructions, we propose a new objective which encourages learning correspondences between similar subtasks by making analogies. For generalization over sequential instructions, we pres…
Enabling autonomous agents to act cooperatively is an important step to integrate artificial intelligence in our daily lives. While some methods seek to stimulate cooperation by letting agents give rewards to others, in this paper we propose a method inspired by the stock market, where agents have the opportunity to participate in other agents' returns by acquiring reward shares. Intuitively, an agent may learn to act according to the common interest when being directly affected by the other agents' rewards. The empirical results of the tested general-sum Markov games show that this mechanism …
Sparse rewards and long time horizons remain challenging for reinforcement learning algorithms. Exploration bonuses can help in sparse reward settings by encouraging agents to explore the state space, while hierarchical approaches can assist with long-horizon tasks by decomposing lengthy tasks into shorter subtasks. We propose HAC Explore (HACx), a new method that combines these approaches by integrating the exploration bonus method Random Network Distillation (RND) into the hierarchical approach Hierarchical Actor-Critic (HAC). HACx outperforms either component method on its own, as well as a…
Zhejiang University（浙江大学）；Westlake University（西湖大学）；UC Berkeley（加州大学伯克利分校）；Institute of Advanced Technology, Westlake Institute for Advanced Study（西湖高等研究院前沿技术研究所）
Unsupervised reinforcement learning aims to acquire skills without prior goal representations, where an agent automatically explores an open-ended environment to represent goals and learn the goal-conditioned policy. However, this procedure is often time-consuming, limiting the rollout in some potentially expensive target environments. The intuitive approach of training in another interaction-rich environment disrupts the reproducibility of trained skills in the target environment due to the dynamics shifts and thus inhibits direct transferring. Assuming free access to a source environment, we…
The MineRL competition is designed for the development of reinforcement learning and imitation learning algorithms that can efficiently leverage human demonstrations to drastically reduce the number of environment interactions needed to solve the complex \emph{ObtainDiamond} task with sparse rewards. To address the challenge, in this paper, we present \textbf{SEIHAI}, a \textbf{S}ample-\textbf{e}ff\textbf{i}cient \textbf{H}ierarchical \textbf{AI}, that fully takes advantage of the human demonstrations and the task structure. Specifically, we split the task into several sequentially dependent s…
In stochastic contextual bandit (SCB) problems, an agent selects an action based on certain observed context to maximize the cumulative reward over iterations. Recently there have been a few studies using a deep neural network (DNN) to predict the expected reward for an action, and the DNN is trained by a stochastic gradient based method. However, convergence analysis has been greatly ignored to examine whether and where these methods converge. In this work, we formulate the SCB that uses a DNN reward function as a non-convex stochastic optimization problem, and design a stage-wise stochastic …
University of California, Berkeley（加州大学伯克利分校）；Carnegie Mellon University（卡内基梅隆大学）；Samsung Research America（三星美国研究院）
Humans are able to understand and perform complex tasks by strategically structuring the tasks into incremental steps or subgoals. For a robot attempting to learn to perform a sequential task with critical subgoal states, such states can provide a natural opportunity for interaction with a human expert. This paper analyzes the benefit of incorporating a notion of subgoals into Inverse Reinforcement Learning (IRL) with a Human-In-The-Loop (HITL) framework. The learning process is interactive, with a human expert first providing input in the form of full demonstrations along with some subgoal st…
Learning from Less: Guiding Deep Reinforcement Learning with Differentiable Symbolic Planning
Computer Science Department, TU Darmstadt（图林大学达姆施塔特分校计算机科学系）；Hessian Center for Artificial Intelligence (hessian.AI)（黑森人工智能中心）；Centre for Cognitive Science, TU Darmstadt（图林大学达姆施塔特分校认知科学中心）；German Research Center for Artificial Intelligence (DFKI)（德国人工智能研究中心）
Demonstration-guided reinforcement learning (RL) is a promising approach for learning complex behaviors by leveraging both reward feedback and a set of target task demonstrations. Prior approaches for demonstration-guided RL treat every new task as an independent learning problem and attempt to follow the provided demonstrations step-by-step, akin to a human trying to imitate a completely unseen behavior by following the demonstrator's exact muscle movements. Naturally, such learning will be slow, but often new behaviors are not completely unseen: they share subtasks with behaviors we have pre…
MARVL: Multi-Stage Guidance for Robotic Manipulation via Vision-Language Models
School of Intelligent Science and Technology, Nanjing University, China（南京大学智能科学与技术学院）；National Key Laboratory for Novel Software Technology, School of Artificial Intelligence, Nanjing University, China（南京大学新型软件技术国家实验室，人工智能学院）；School of Artificial Intelligence, Nanjing University, China（南京大学人工智能学院）；MACS Lab, University of Washington（华盛顿大学MACS实验室）
Typical reinforcement learning (RL) agents learn to complete tasks specified by reward functions tailored to their domain. As such, the policies they learn do not generalize even to similar domains. To address this issue, we develop a framework through which a deep RL agent learns to generalize policies from smaller, simpler domains to more complex ones using a recurrent attention mechanism. The task is presented to the agent as an image and an instruction specifying the goal. This meta-controller guides the agent towards its goal by designing a sequence of smaller subtasks on the part of the …
Long-Horizon-Terminal-Bench: Testing the Limits of Agents on Long-Horizon Terminal Tasks with Dense Reward-Based Grading
Tencent（腾讯）；University of Maryland, College Park（马里兰大学帕克分校）；University of Georgia（佐治亚大学）；University of Minnesota, Twin Cities（明尼苏达大学双城分校）；Indiana University（印第安纳大学）；Lehigh University（里海大学）；National University of Singapore（新加坡国立大学）；The Hong Kong Polytechnic University（香港理工大学）
UC Berkeley（加州大学伯克利分校）；Google Research（谷歌研究院）；University of Toronto（多伦多大学）；Covariant（协变机器人公司）
Intelligent agents need to select long sequences of actions to solve complex tasks. While humans easily break down tasks into subgoals and reach them through millions of muscle commands, current artificial intelligence is limited to tasks with horizons of a few hundred decisions, despite large compute budgets. Research on hierarchical reinforcement learning aims to overcome this limitation but has proven to be challenging, current methods rely on manually specified goal spaces or subtasks, and no general solution exists. We introduce Director, a practical method for learning hierarchical behav…
University of Geneva（日内瓦大学）；University of Applied Sciences Western Switzerland（瑞士西部应用科学大学）；University College London（伦敦大学学院）；Alan Turing Institute（阿兰·图灵研究所）
Despite recent advances, goal-directed generation of structured discrete data remains challenging. For problems such as program synthesis (generating source code) and materials design (generating molecules), finding examples which satisfy desired constraints or exhibit desired properties is difficult. In practice, expensive heuristic search or reinforcement learning algorithms are often employed. In this paper we investigate the use of conditional generative models which directly attack this inverse problem, by modeling the distribution of discrete structures given properties of interest. Unfo…
