We study reward design strategies for incentivizing a reinforcement learning agent to adopt a policy from a set of admissible policies. The goal of the reward designer is to modify the underlying reward function cost-efficiently while ensuring that any approximately optimal deterministic policy under the new reward function is admissible and performs well under the original reward function. This problem can be viewed as a dual to the problem of optimal reward poisoning attacks: instead of forcing an agent to adopt a specific policy, the reward designer incentivizes an agent to avoid taking actions that are inadmissible in certain states. Perhaps surprisingly, and in contrast to the problem of optimal reward poisoning attacks, we first show that the reward design problem for admissible policy teaching is computationally challenging, and it is NP-hard to find an approximately optimal reward modification. We then proceed by formulating a surrogate problem whose optimal solution approximates the optimal solution to the reward design problem in our setting, but is more amenable to optimization techniques and analysis. For this surrogate problem, we present characterization results that provide bounds on the value of the optimal solution. Finally, we design a local search algorithm to solve the surrogate problem and showcase its utility using simulation-based experiments.
School of Engineering & IT University of New South Wales Canberra（新南威尔士大学堪培拉校区工程与信息技术学院）
The design of reward functions in reinforcement learning is a human skill that comes with experience. Unfortunately, there is not any methodology in the literature that could guide a human to design the reward function or to allow a human to transfer the skills developed in designing reward functions to another human and in a systematic manner. In this paper, we use Systematic Instructional Design, an approach in human education, to engineer a machine education methodology to design reward functions for reinforcement learning. We demonstrate the methodology in designing a hierarchical genetic …
A key impediment to reinforcement learning (RL) in real applications with limited, batch data is defining a reward function that reflects what we implicitly know about reasonable behaviour for a task and allows for robust off-policy evaluation. In this work, we develop a method to identify an admissible set of reward functions for policies that (a) do not diverge too far from past behaviour, and (b) can be evaluated with high confidence, given only a collection of past trajectories. Together, these ensure that we propose policies that we trust to be implemented in high-risk settings. We demons…
Inverse reinforcement learning (IRL) infers a reward function from demonstrations, allowing for policy improvement and generalization. However, despite much recent interest in IRL, little work has been done to understand the minimum set of demonstrations needed to teach a specific sequential decision-making task. We formalize the problem of finding maximally informative demonstrations for IRL as a machine teaching problem where the goal is to find the minimum number of demonstrations needed to specify the reward equivalence class of the demonstrator. We extend previous work on algorithmic teac…
We study the sample complexity of teaching, termed as "teaching dimension" (TDim) in the literature, for the teaching-by-reinforcement paradigm, where the teacher guides the student through rewards. This is distinct from the teaching-by-demonstration paradigm motivated by robotics applications, where the teacher teaches by providing demonstrations of state/action trajectories. The teaching-by-reinforcement paradigm applies to a wider range of real-world settings where a demonstration is inconvenient, but has not been studied systematically. In this paper, we focus on a specific family of reinf…
Max Planck Institute for Software Systems (MPI-SWS)（马克斯·普朗克软件系统研究所）；University of Wisconsin-Madison（威斯康星大学麦迪逊分校）
We study a security threat to reinforcement learning where an attacker poisons the learning environment to force the agent into executing a target policy chosen by the attacker. As a victim, we consider RL agents whose objective is to find a policy that maximizes reward in infinite-horizon problem settings. The attacker can manipulate the rewards and the transition dynamics in the learning environment at training-time, and is interested in doing so in a stealthy manner. We propose an optimization framework for finding an optimal stealthy attack for different measures of attack cost. We provide…
Learning from demonstrations is a popular tool for accelerating and reducing the exploration requirements of reinforcement learning. When providing expert demonstrations to human students, we know that the demonstrations must fall within a particular range of difficulties called the "Zone of Proximal Development (ZPD)". If they are too easy the student learns nothing, but if they are too difficult the student is unable to follow along. This raises the question: Given a set of potential demonstrators, which among them is best suited for teaching any particular learner? Prior work, such as the p…
Max Planck Institute for Software Systems (MPI-SWS)（马克斯·普朗克软件系统研究所）；University of Wisconsin-Madison（威斯康星大学麦迪逊分校）
We study a security threat to reinforcement learning where an attacker poisons the learning environment to force the agent into executing a target policy chosen by the attacker. As a victim, we consider RL agents whose objective is to find a policy that maximizes average reward in undiscounted infinite-horizon problem settings. The attacker can manipulate the rewards or the transition dynamics in the learning environment at training-time and is interested in doing so in a stealthy manner. We propose an optimization framework for finding an \emph{optimal stealthy attack} for different measures …
Reward design for reinforcement learning agents can be difficult in situations where one not only wants the agent to achieve some effect in the world but where one also cares about how that effect is achieved. For example, we might wish for an agent to adhere to a tacit understanding of commonsense, align itself to a preference for how to behave for purposes of safety, or taking on a particular role in an interactive game. Storytelling is a mode for communicating tacit procedural knowledge. We introduce a technique, Story Shaping, in which a reinforcement learning agent infers tacit knowledge …
ETH Zurich（苏黎世联邦理工学院）；Microsoft Research（微软研究院）；Max Planck Institute for Software Systems（马克斯·普朗克软件系统研究所）
Learning near-optimal behaviour from an expert's demonstrations typically relies on the assumption that the learner knows the features that the true reward function depends on. In this paper, we study the problem of learning from demonstrations in the setting where this is not the case, i.e., where there is a mismatch between the worldviews of the learner and the expert. We introduce a natural quantity, the teaching risk, which measures the potential suboptimality of policies that look optimal to the learner in this setting. We show that bounds on the teaching risk guarantee that the learner i…
KAIST（韩国科学技术院）；University of Michigan（密歇根大学）；LG AI Research（LG人工智能研究院）；UC Berkeley（加州大学伯克利分校）
Preference-based reinforcement learning (RL) has shown potential for teaching agents to perform the target tasks without a costly, pre-defined reward function by learning the reward with a supervisor's preference between the two agent behaviors. However, preference-based learning often requires a large amount of human feedback, making it difficult to apply this approach to various applications. This data-efficiency problem, on the other hand, has been typically addressed by using unlabeled samples or data augmentation techniques in the context of supervised learning. Motivated by the recent su…
The Swiss AI Lab, IDSIA（瑞士人工智能实验室（IDSIA））；USI（意大利语区大学）；SUPSI（瑞士南部应用科学与艺术大学）；NNAISENSE
We transform reinforcement learning (RL) into a form of supervised learning (SL) by turning traditional RL on its head, calling this Upside Down RL (UDRL). Standard RL predicts rewards, while UDRL instead uses rewards as task-defining inputs, together with representations of time horizons and other computable functions of historic and desired future data. UDRL learns to interpret these input observations as commands, mapping them to actions (or action probabilities) through SL on past (possibly accidental) experience. UDRL generalizes to achieve high rewards or other goals, through input comma…
Brown University（布朗大学）；AI Impacts；Stanford University（斯坦福大学）；University of Oxford（牛津大学）
Providing Reinforcement Learning agents with expert advice can dramatically improve various aspects of learning. Prior work has developed teaching protocols that enable agents to learn efficiently in complex environments; many of these methods tailor the teacher's guidance to agents with a particular representation or underlying learning scheme, offering effective but specialized teaching procedures. In this work, we explore protocol programs, an agent-agnostic schema for Human-in-the-Loop Reinforcement Learning. Our goal is to incorporate the beneficial properties of a human teacher into Rein…
Teaching LLMs for Step-Level Automatic Math Correction via Reinforcement Learning
School of Computer Science and Technology, East China Normal University（华东师范大学计算机科学与技术学院）；Lab of AI for Education, East China Normal University（华东师范大学教育人工智能实验室）
University of Lincoln（林肯大学）；Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院）
Deep Reinforcement Learning (DRL) is a promising approach for teaching robots new behaviour. However, one of its main limitations is the need for carefully hand-coded reward signals by an expert. We argue that it is crucial to automate the reward learning process so that new skills can be taught to robots by their users. To address such automation, we consider task success classifiers using visual observations to estimate the rewards in terms of task success. In this work, we study the performance of multiple state-of-the-art deep reinforcement learning algorithms under different types of rewa…
Classical control techniques such as PID and LQR have been used effectively in maintaining a system state, but these techniques become more difficult to implement when the model dynamics increase in complexity and sensitivity. For adaptive robotic locomotion tasks with several degrees of freedom, this task becomes infeasible with classical control techniques. Instead, reinforcement learning can train optimal walking policies with ease. We apply deep Q-learning and augmented random search (ARS) to teach a simulated two-dimensional bipedal robot how to walk using the OpenAI Gym BipedalWalker-v3 …
Reward learning enables robots to learn adaptable behaviors from human input. Traditional methods model the reward as a linear function of hand-crafted features, but that requires specifying all the relevant features a priori, which is impossible for real-world tasks. To get around this issue, recent deep Inverse Reinforcement Learning (IRL) methods learn rewards directly from the raw state but this is challenging because the robot has to implicitly learn the features that are important and how to combine them, simultaneously. Instead, we propose a divide and conquer approach: focus human inpu…
We explore unconstrained natural language feedback as a learning signal for artificial agents. Humans use rich and varied language to teach, yet most prior work on interactive learning from language assumes a particular form of input (e.g., commands). We propose a general framework which does not make this assumption, using aspect-based sentiment analysis to decompose feedback into sentiment about the features of a Markov decision process. We then perform an analogue of inverse reinforcement learning, regressing the sentiment on the features to infer the teacher's latent reward function. To ev…
Learning from Demonstration (LfD) seeks to democratize robotics by enabling non-roboticist end-users to teach robots to perform a task by providing a human demonstration. However, modern LfD techniques, e.g. inverse reinforcement learning (IRL), assume users provide at least stochastically optimal demonstrations. This assumption fails to hold in most real-world scenarios. Recent attempts to learn from sub-optimal demonstration leverage pairwise rankings and following the Luce-Shepard rule. However, we show these approaches make incorrect assumptions and thus suffer from brittle, degraded perfo…
KTH Royal Institute of Technology（瑞典皇家理工学院）；Institute for Systems and Robotics, Instituto Superior Técnico（高等技术学院系统与机器人研究所）
Time perception is the phenomenological experience of time by an individual. In this paper, we study how to replicate neural mechanisms involved in time perception, allowing robots to take a step towards temporal cognition. Our framework follows a twofold biologically inspired approach. The first step consists of estimating the passage of time from sensor measurements, since environmental stimuli influence the perception of time. Sensor data is modeled as Gaussian processes that represent the second-order statistics of the natural environment. The estimated elapsed time between two events is c…
University of Maryland（马里兰大学）；Microsoft Research（微软研究院）；Rutgers University（罗格斯大学）
We present a novel interactive learning protocol that enables training request-fulfilling agents by verbally describing their activities. Unlike imitation learning (IL), our protocol allows the teaching agent to provide feedback in a language that is most appropriate for them. Compared with reward in reinforcement learning (RL), the description feedback is richer and allows for improved sample complexity. We develop a probabilistic framework and an algorithm that practically implements our protocol. Empirical results in two challenging request-fulfilling problems demonstrate the strengths of o…
Conservative Bias in Multi-Teacher Learning: Why Agents Prefer Low-Reward Advisors
School of Computer Science and Engineering, University of New South Wales（新南威尔士大学计算机科学与工程学院）；Escuela de Ingeniería, Universidad Central de Chile（智利中央大学工程学院）
Uncertainty-aware Reward Model: Teaching Reward Models to Know What is Unknown
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；Baichuan Inc.（百川公司）；Tsinghua University（清华大学）
RL4RLA: Teaching ML to Discover Randomized Linear Algebra Algorithms Through Curriculum Design and Graph-Based Search
Pratt School of Engineering, Duke University, Durham, NC, USA（杜克大学工程学院）；Department of Computer Science, Dartmouth College, Hanover, NH, USA（达特茅斯学院计算机科学系）
Institut des Systèmes Intelligents et de Robotique Sorbonne Université, CNRS UMR 7222（索邦大学智能系统与机器人研究所（法国国家科学研究中心UMR 7222））；FLOWERS Team INRIA Bordeaux Sud Ouest（法国国家信息与自动化研究所波尔多西南 Flowers 团队）
In this paper we study a new reinforcement learning setting where the environment is non-rewarding, contains several possibly related objects of various controllability, and where an apt agent Bob acts independently, with non-observable intentions. We argue that this setting defines a realistic scenario and we present a generic discrete-state discrete-action model of such environments. To learn in this environment, we propose an unsupervised reinforcement learning agent called CLIC for Curriculum Learning and Imitation for Control. CLIC learns to control individual objects in its environment, …
Text-based games are a natural challenge domain for deep reinforcement learning algorithms. Their state and action spaces are combinatorially large, their reward function is sparse, and they are partially observable: the agent is informed of the consequences of its actions through textual feedback. In this paper we emphasize this latter point and consider the design of a deep reinforcement learning agent that can play from feedback alone. Our design recognizes and takes advantage of the structural characteristics of text-based games. We first propose a contextualisation mechanism, based on acc…
Institut d’intelligence aritficielle du Québec (Mila)（魁北克人工智能研究所（Mila））；École Polytechnique de Montréal（蒙特利尔理工学院）；Ubisoft La Forge（育碧La Forge实验室）；Université de Montréal（蒙特利尔大学）；ServiceNow（ServiceNow公司）
The standard formulation of Reinforcement Learning lacks a practical way of specifying what are admissible and forbidden behaviors. Most often, practitioners go about the task of behavior specification by manually engineering the reward function, a counter-intuitive process that requires several iterations and is prone to reward hacking by the agent. In this work, we argue that constrained RL, which has almost exclusively been used for safe RL, also has the potential to significantly reduce the amount of work spent for reward specification in applied RL projects. To this end, we propose to spe…
Allen Institute for AI（艾伦人工智能研究院）；University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
In practice, imitation learning is preferred over pure reinforcement learning whenever it is possible to design a teaching agent to provide expert supervision. However, we show that when the teaching agent makes decisions with access to privileged information that is unavailable to the student, this information is marginalized during imitation learning, resulting in an "imitation gap" and, potentially, poor results. Prior work bridges this gap via a progression from imitation learning to reinforcement learning. While often successful, gradual progression fails for tasks that require frequent s…
Policy and World Modeling Co-Training for Language Agents
Southern University of Science and Technology（南方科技大学）；Hong Kong University of Science and Technology（香港科学大学）；Hong Kong University of Science and Technology (Guangzhou)（香港科学大学（广州））；Hong Kong Polytechnic University（香港理工大学）；LIGHTSPEED
