Training deep reinforcement learning agents complex behaviors in 3D virtual environments requires significant computational resources. This is especially true in environments with high degrees of aliasing, where many states share nearly identical visual features. Minecraft is an exemplar of such an environment. We hypothesize that interactive machine learning IML, wherein human teachers play a direct role in training through demonstrations, critique, or action advice, may alleviate agent susceptibility to aliasing. However, interactive machine learning is only practical when the number of human interactions is limited, requiring a balance between human teacher effort and agent performance. We conduct experiments with two reinforcement learning algorithms which enable human teachers to give action advice, Feedback Arbitration and Newtonian Action Advice, under visual aliasing conditions. To assess potential cognitive load per advice type, we vary the accuracy and frequency of various human action advice techniques. Training efficiency, robustness against infrequent and inaccurate advisor input, and sensitivity to aliasing are examined.
Technische Universität Berlin（柏林工业大学）；Department of Electrical Engineering and Computer Science（电气工程与计算机科学系）；Berlin, Germany（德国柏林（仅保留城市名，未明确机构））
Deep reinforcement learning has been successfully applied to several visual-input tasks using model-free methods. In this paper, we propose a model-based approach that combines learning a DNN-based transition model with Monte Carlo tree search to solve a block-placing task in Minecraft. Our learned transition model predicts the next frame and the rewards one step ahead given the last four frames of the agent's first-person-view image and the current action. Then a Monte Carlo tree search algorithm uses this model to plan the best sequence of actions for the agent to perform. On the proposed ta…
University of Applied Sciences Northwestern Switzerland（瑞士西北应用科学大学）
Sample inefficiency of deep reinforcement learning methods is a major obstacle for their use in real-world applications. In this work, we show how human demonstrations can improve final performance of agents on the Minecraft minigame ObtainDiamond with only 8M frames of environment interaction. We propose a training procedure where policy networks are first trained on human data and later fine-tuned by reinforcement learning. Using a policy exploitation mechanism, experience replay and an additional loss against catastrophic forgetting, our best agent was able to achieve a mean score of 48. Ou…
Learning rational behaviors in open-world games like Minecraft remains to be challenging for Reinforcement Learning (RL) research due to the compound challenge of partial observability, high-dimensional visual perception and delayed reward. To address this, we propose JueWu-MC, a sample-efficient hierarchical RL approach equipped with representation learning and imitation learning to deal with perception and exploration. Specifically, our approach includes two levels of hierarchy, where the high-level controller learns a policy to control over options and the low-level workers learn to solve e…
Many currently deployed Reinforcement Learning agents work in an environment shared with humans, be them co-workers, users or clients. It is desirable that these agents adjust to people's preferences, learn faster thanks to their help, and act safely around them. We argue that most current approaches that learn from human feedback are unsafe: rewarding or punishing the agent a-posteriori cannot immediately prevent it from wrong-doing. In this paper, we extend Policy Gradient to make it robust to external directives, that would otherwise break the fundamentally on-policy nature of Policy Gradie…
In this paper, we introduce a new set of reinforcement learning (RL) tasks in Minecraft (a flexible 3D world). We then use these tasks to systematically compare and contrast existing deep reinforcement learning (DRL) architectures with our new memory-based DRL architectures. These tasks are designed to emphasize, in a controllable manner, issues that pose challenges for RL methods including partial observability (due to first-person visual observations), delayed rewards, high-dimensional visual observations, and the need to use active perception in a correct manner so as to perform well in the…
University of Toronto（多伦多大学）；Vector Institute（向量研究所）；Google Brain（谷歌大脑）
Sparse reward is one of the most challenging problems in reinforcement learning (RL). Hindsight Experience Replay (HER) attempts to address this issue by converting a failed experience to a successful one by relabeling the goals. Despite its effectiveness, HER has limited applicability because it lacks a compact and universal goal representation. We present Augmenting experienCe via TeacheR's adviCE (ACTRCE), an efficient reinforcement learning technique that extends the HER framework using natural language as the goal representation. We first analyze the differences among goal representation,…
Training automated agents to complete complex tasks in interactive environments is challenging: reinforcement learning requires careful hand-engineering of reward functions, imitation learning requires specialized infrastructure and access to a human expert, and learning from intermediate forms of supervision (like binary preferences) is time-consuming and extracts little information from each human intervention. Can we overcome these challenges by building agents that learn from rich, interactive feedback instead? We propose a new supervision paradigm for interactive learning based on "teacha…
Carnegie Mellon University（卡内基梅隆大学）；INRIA Lille - Nord Europe（里尔-北欧法国国家信息与自动化研究所）
In some reinforcement learning problems an agent may be provided with a set of input policies, perhaps learned from prior experience or provided by advisors. We present a reinforcement learning with policy advice (RLPA) algorithm which leverages this input set and learns to use the best policy in the set for the reinforcement learning task at hand. We prove that RLPA has a sub-linear regret of \tilde O(\sqrt{T}) relative to the best input policy, and that both this regret and its computational complexity are independent of the size of the state and action space. Our empirical simulations suppo…
Laboratoire de Neurosciences Cognitives Computationnelles (LNC2)（计算认知神经科学实验室（LNC2））；INSERM U960（法国国家健康与医学研究院 U960）；Institute for Intelligent Systems and Robotics（智能系统与机器人研究所）；Sorbonne Université（索邦大学）；CNRS UMR 7222（法国国家科学研究中心 UMR 7222）
In this paper, we provide an overview of the existing methods for integrating human advice into a Reinforcement Learning process. We first propose a taxonomy of the different forms of advice that can be provided to a learning agent. We then describe the methods that can be used for interpreting advice when its meaning is not determined beforehand. Finally, we review different approaches for integrating advice into the learning process.
We propose a lifelong learning system that has the ability to reuse and transfer knowledge from one task to another while efficiently retaining the previously learned knowledge-base. Knowledge is transferred by learning reusable skills to solve tasks in Minecraft, a popular video game which is an unsolved and high-dimensional lifelong learning problem. These reusable skills, which we refer to as Deep Skill Networks, are then incorporated into our novel Hierarchical Deep Reinforcement Learning Network (H-DRLN) architecture using two techniques: (1) a deep skill array and (2) skill distillation,…
University of Washington（华盛顿大学）；Western Washington University（西华盛顿大学）
Reinforcement learning involves agents interacting with an environment to complete tasks. When rewards provided by the environment are sparse, agents may not receive immediate feedback on the quality of actions that they take, thereby affecting learning of policies. In this paper, we propose to methods to augment the reward signal from the environment with an additional reward termed shaping advice in both single and multi-agent reinforcement learning. The shaping advice is specified as a difference of potential functions at consecutive time-steps. Each potential function is a function of obse…
University of New South Wales（新南威尔士大学）；Federation University（联邦大学）；Deakin University（迪肯大学）
The use of interactive advice in reinforcement learning scenarios allows for speeding up the learning process for autonomous agents. Current interactive reinforcement learning research has been limited to real-time interactions that offer relevant user advice to the current state only. Moreover, the information provided by each interaction is not retained and instead discarded by the agent after a single use. In this paper, we present a method for retaining and reusing provided knowledge, allowing trainers to give general advice relevant to more than just the current state. Results obtained sh…
Washington State University（华盛顿州立大学）；Princeton University（普林斯顿大学）
Policy advice is a transfer learning method where a student agent is able to learn faster via advice from a teacher. However, both this and other reinforcement learning transfer methods have little theoretical analysis. This paper formally defines a setting where multiple teacher agents can provide advice to a student and introduces an algorithm to leverage both autonomous exploration and teacher's advice. Our regret bounds justify the intuition that good teachers help while bad teachers hurt. Using our formalization, we are also able to quantify, for the first time, when negative transfer can…
Action advising is a peer-to-peer knowledge exchange technique built on the teacher-student paradigm to alleviate the sample inefficiency problem in deep reinforcement learning. Recently proposed student-initiated approaches have obtained promising results. However, due to being in the early stages of development, these also have some substantial shortcomings. One of the abilities that are absent in the current methods is further utilising advice by reusing, which is especially crucial in the practical settings considering the budget and cost constraints in peer-to-peer. In this study, we pres…
Interactive reinforcement learning agents use human feedback or instruction to help them learn in complex environments. Often, this feedback comes in the form of a discrete signal that is either positive or negative. While informative, this information can be difficult to generalize on its own. In this work, we explore how natural language advice can be used to provide a richer feedback signal to a reinforcement learning agent by extending policy shaping, a well-known Interactive reinforcement learning technique. Usually policy shaping employs a human feedback policy to help an agent to learn …
Human-in-the-loop (HiL) reinforcement learning is gaining traction in domains with large action and state spaces, and sparse rewards by allowing the agent to take advice from HiL. Beyond advice accommodation, a sequential decision-making agent must be able to express the extent to which it was able to utilize the human advice. Subsequently, the agent should provide a means for the HiL to inspect parts of advice that it had to reject in favor of the overall environment objective. We introduce the problem of Advice-Conformance Verification which requires reinforcement learning (RL) agents to pro…
Alberta Machine Intelligence Institute (Amii)（阿尔伯塔机器智能研究所（Amii））；University of Alberta（阿尔伯塔大学）；Queen Mary University of London（伦敦玛丽女王大学）
Reinforcement learning (RL) has shown great success in solving many challenging tasks via use of deep neural networks. Although using deep learning for RL brings immense representational power, it also causes a well-known sample-inefficiency problem. This means that the algorithms are data-hungry and require millions of training samples to converge to an adequate policy. One way to combat this issue is to use action advising in a teacher-student framework, where a knowledgeable teacher provides action advice to help the student. This work considers how to better leverage uncertainties about wh…
An important challenge in reinforcement learning is training agents that can solve a wide variety of tasks. If tasks depend on each other (e.g. needing to learn to walk before learning to run), curriculum learning can speed up learning by focusing on the next best task to learn. We explore curriculum learning in a complex, visual domain with many hard exploration challenges: Minecraft. We find that learning progress (defined as a change in success probability of a task) is a reliable measure of learnability for automatically constructing an effective curriculum. We introduce a learning-progres…
Multi-agent reinforcement learning involves multiple agents interacting with each other and a shared environment to complete tasks. When rewards provided by the environment are sparse, agents may not receive immediate feedback on the quality of actions that they take, thereby affecting learning of policies. In this paper, we propose a method called Shaping Advice in deep Multi-agent reinforcement learning (SAM) to augment the reward signal from the environment with an additional reward termed shaping advice. The shaping advice is given by a difference of potential functions at consecutive time…
Federation University（联邦大学）；Deakin University（迪肯大学）；Universidad Central de Chile（智利中央大学）
Interactive reinforcement learning proposes the use of externally-sourced information in order to speed up the learning process. When interacting with a learner agent, humans may provide either evaluative or informative advice. Prior research has focused on the effect of human-sourced advice by including real-time feedback on the interactive reinforcement learning process, specifically aiming to improve the learning speed of the agent, while minimising the time demands on the human. This work focuses on answering which of two approaches, evaluative or informative, is the preferred instructiona…
Aristotle University of Thessaloniki（塞萨洛尼基亚里士多德大学）；Washington State University（华盛顿州立大学）
In this article we study the transfer learning model of action advice under a budget. We focus on reinforcement learning teachers providing action advice to heterogeneous students playing the game of Pac-Man under a limited advice budget. First, we examine several critical factors affecting advice quality in this setting, such as the average performance of the teacher, its variance and the importance of reward discounting in advising. The experiments show the non-trivial importance of the coefficient of variation (CV) as a statistic for choosing policies that generate advice. The CV statistic …
Federation University（澳大利亚联邦大学）；Deakin University（迪肯大学）；Universidad Central de Chile（智利中央大学）
Interactive reinforcement learning has allowed speeding up the learning process in autonomous agents by including a human trainer providing extra information to the agent in real-time. Current interactive reinforcement learning research has been limited to real-time interactions that offer relevant user advice to the current state only. Additionally, the information provided by each interaction is not retained and instead discarded by the agent after a single-use. In this work, we propose a persistent rule-based interactive reinforcement learning approach, i.e., a method for retaining and reus…
Auto MC-Reward: Automated Dense Reward Design with Large Language Models for Minecraft
CUHK-SenseTime Joint Laboratory, The Chinese University of Hong Kong（香港中文大学-商汤科技联合实验室，香港中文大学）；OpenGVLab, Shanghai AI Laboratory（上海人工智能实验室，OpenGVLab）；Tsinghua University（清华大学）；SenseTime Research（商汤科技研究院）；Shanghai Jiao Tong University（上海交通大学）
Solving portfolio management problems using deep reinforcement learning has been getting much attention in finance for a few years. We have proposed a new method using experts signals and historical price data to feed into our reinforcement learning framework. Although experts signals have been used in previous works in the field of finance, as far as we know, it is the first time this method, in tandem with deep RL, is used to solve the financial portfolio management problem. Our proposed framework consists of a convolutional network for aggregating signals, another convolutional network for …
One of the main questions concerning learning in Multi-Agent Systems is: (How) can agents benefit from mutual interaction during the learning process?. This paper describes the study of an interactive advice-exchange mechanism as a possible way to improve agents' learning performance. The advice-exchange technique, discussed here, uses supervised learning (backpropagation), where reinforcement is not directly coming from the environment but is based on advice given by peers with better performance score (higher confidence), to enhance the performance of a heterogeneous group of Learning Agents…
Tsinghua University（清华大学）；Louisiana State University（路易斯安那州立大学）
Learning to coordinate is a daunting problem in multi-agent reinforcement learning (MARL). Previous works have explored it from many facets, including cognition between agents, credit assignment, communication, expert demonstration, etc. However, less attention were paid to agents' decision structure and the hierarchy of coordination. In this paper, we explore the spatiotemporal structure of agents' decisions and consider the hierarchy of coordination from the perspective of multilevel emergence dynamics, based on which a novel approach, Learning to Advise and Learning from Advice (LALA), is p…
High-dimensional observations and complex real-world dynamics present major challenges in reinforcement learning for both function approximation and exploration. We address both of these challenges with two complementary techniques: First, we develop a gradient-boosting style, non-parametric function approximator for learning on $Q$-function residuals. And second, we propose an exploration strategy inspired by the principles of state abstraction and information acquisition under uncertainty. We demonstrate the empirical effectiveness of these techniques, first, as a preliminary check, on two s…
Deep reinforcement learning algorithms that estimate state and state-action value functions have been shown to be effective in a variety of challenging domains, including learning control strategies from raw image pixels. However, algorithms that estimate state and state-action value functions typically assume a fully observed state and must compensate for partial observations by using finite length observation histories or recurrent networks. In this work, we propose a new deep reinforcement learning algorithm based on counterfactual regret minimization that iteratively updates an approximati…
Ghost in the Minecraft: Generally Capable Agents for Open-World Environments via Large Language Models with Text-based Knowledge and Memory
Tsinghua University（清华大学）；SenseTime Research（商汤科技研究院）；University of Science and Technology of China（中国科学技术大学）；The Chinese University of Hong Kong（香港中文大学）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；Institute of Automation, Chinese Academy of Science (CASIA)（中国科学院自动化研究所）；Centre for Artificial Intelligence and Robotics, HKISI, CAS（中国科学院香港创新研究院人工智能与机器人创新中心）
Sparebank 1 SR-Bank（Sparebank 1 SR银行）；Center for Artificial Intelligence Research（人工智能研究中心）；University of Agder（阿格德大学）
Personalisation of products and services is fast becoming the driver of success in banking and commerce. Machine learning holds the promise of gaining a deeper understanding of and tailoring to customers' needs and preferences. Whereas traditional solutions to financial decision problems frequently rely on model assumptions, reinforcement learning is able to exploit large amounts of data to improve customer modelling and decision-making in complex financial environments with fewer assumptions. Model explainability and interpretability present challenges from a regulatory perspective which dema…
Despite rapid progress in theoretical reinforcement learning (RL) over the last few years, most of the known guarantees are worst-case in nature, failing to take advantage of structure that may be known a priori about a given RL problem at hand. In this paper we address the question of whether worst-case lower bounds for regret in online learning of Markov decision processes (MDPs) can be circumvented when information about the MDP, in the form of predictions about its optimal $Q$-value function, is given to the algorithm. We show that when the predictions about the optimal $Q$-value function …
Action advising is a budget-constrained knowledge exchange mechanism between teacher-student peers that can help tackle exploration and sample inefficiency problems in deep reinforcement learning (RL). Most recently, student-initiated techniques that utilise state novelty and uncertainty estimations have obtained promising results. However, the approaches built on these estimations have some potential weaknesses. First, they assume that the convergence of the student's RL model implies less need for advice. This can be misleading in scenarios with teacher absence early on where the student is …
Deep Reinforcement Learning (DeepRL) methods have been widely used in robotics to learn about the environment and acquire behaviors autonomously. Deep Interactive Reinforcement Learning (DeepIRL) includes interactive feedback from an external trainer or expert giving advice to help learners choosing actions to speed up the learning process. However, current research has been limited to interactions that offer actionable advice to only the current state of the agent. Additionally, the information is discarded by the agent after a single use that causes a duplicate process at the same state for …
University of Washington（华盛顿大学）；Worcester Polytechnic Institute（伍斯特理工学院）
This paper augments the reward received by a reinforcement learning agent with potential functions in order to help the agent learn (possibly stochastic) optimal policies. We show that a potential-based reward shaping scheme is able to preserve optimality of stochastic policies, and demonstrate that the ability of an agent to learn an optimal policy is not affected when this scheme is augmented to soft Q-learning. We propose a method to impart potential based advice schemes to policy gradient algorithms. An algorithm that considers an advantage actor-critic architecture augmented with this sch…
Deep hierarchical reinforcement learning has gained a lot of attention in recent years due to its ability to produce state-of-the-art results in challenging environments where non-hierarchical frameworks fail to learn useful policies. However, as problem domains become more complex, deep hierarchical reinforcement learning can become inefficient, leading to longer convergence times and poor performance. We introduce the Deep Nested Agent framework, which is a variant of deep hierarchical reinforcement learning where information from the main agent is propagated to the low level $nested$ agent …
University of Alberta（阿尔伯塔大学）；Google, DeepMind（谷歌深度思维）
Reinforcement learning is a powerful learning paradigm in which agents can learn to maximize sparse and delayed reward signals. Although RL has had many impressive successes in complex domains, learning can take hours, days, or even years of training data. A major challenge of contemporary RL research is to discover how to learn with less data. Previous work has shown that domain information can be successfully used to shape the reward; by adding additional reward information, the agent can learn with much less data. Furthermore, if the reward is constructed from a potential function, the opti…
We consider tackling a single-agent RL problem by distributing it to $n$ learners. These learners, called advisors, endeavour to solve the problem from a different focus. Their advice, taking the form of action values, is then communicated to an aggregator, which is in control of the system. We show that the local planning method for the advisors is critical and that none of the ones found in the literature is flawless: the egocentric planning overestimates values of states where the other advisors disagree, and the agnostic planning is inefficient around danger zones. We introduce a novel app…
Model-based reinforcement learning algorithms are typically more sample efficient than their model-free counterparts, especially in sparse reward problems. Unfortunately, many interesting domains are too complex to specify the complete models required by traditional model-based approaches. Learning a model takes a large number of environment samples, and may not capture critical information if the environment is hard to explore. If we could specify an incomplete model and allow the agent to learn how best to use it, we could take advantage of our partial understanding of many domains. Existing…
We describe a method to use discrete human feedback to enhance the performance of deep learning agents in virtual three-dimensional environments by extending deep-reinforcement learning to model the confidence and consistency of human feedback. This enables deep reinforcement learning algorithms to determine the most appropriate time to listen to the human feedback, exploit the current policy model, or explore the agent's environment. Managing the trade-off between these three strategies allows DRL agents to be robust to inconsistent or intermittent human feedback. Through experimentation usin…
Artificial Intelligence Research Institute FRC CSC RAS（俄罗斯科学院计算机科学与控制研究中心人工智能研究所）；Moscow Institute of Physics and Technology（莫斯科物理技术学院）；Higher School of Economics（高等经济学院）；Moscow Aviation Institute（莫斯科航空学院）
Currently, deep reinforcement learning (RL) shows impressive results in complex gaming and robotic environments. Often these results are achieved at the expense of huge computational costs and require an incredible number of episodes of interaction between the agent and the environment. There are two main approaches to improving the sample efficiency of reinforcement learning methods - using hierarchical methods and expert demonstrations. In this paper, we propose a combination of these approaches that allow the agent to use low-quality demonstrations in complex vision-based environments with …
Deep Reinforcement Learning (RL) techniques can benefit greatly from leveraging prior experience, which can be either self-generated or acquired from other entities. Action advising is a framework that provides a flexible way to transfer such knowledge in the form of actions between teacher-student peers. However, due to the realistic concerns, the number of these interactions is limited with a budget; therefore, it is crucial to perform these in the most appropriate moments. There have been several promising studies recently that address this problem setting especially from the student's pers…
RL-GPT: Integrating Reinforcement Learning and Code-as-policy
The Chinese University of Hong Kong（香港中文大学）；School of Computer Science, Peking University（北京大学计算机学院）；SmartMore（智谱AI）；Beijing Academy of Artificial Intelligence（北京智源人工智能研究院）
本文提出双层级框架 RL-GPT，通过慢智能体进行代码规划、快智能体结合强化学习执行低层动作，在 Minecraft 和 MineDojo 中实现高效率与 SOTA 表现。
To widen their accessibility and increase their utility, intelligent agents must be able to learn complex behaviors as specified by (non-expert) human users. Moreover, they will need to learn these behaviors within a reasonable amount of time while efficiently leveraging the sparse feedback a human trainer is capable of providing. Recent work has shown that human feedback can be characterized as a critique of an agent's current behavior rather than as an alternative reward signal to be maximized, culminating in the COnvergent Actor-Critic by Humans (COACH) algorithm for making direct policy up…
