This work provides a thorough study on how reward scaling can affect performance of deep reinforcement learning agents. In particular, we would like to answer the question that how does reward scaling affect non-saturating ReLU networks in RL? This question matters because ReLU is one of the most effective activation functions for deep learning models. We also propose an Adaptive Network Scaling framework to find a suitable scale of the rewards during learning for better performance. We conducted empirical studies to justify the solution.
University of Oxford（牛津大学）；University of Michigan, Ann Arbor（密歇根大学安娜堡分校）
We present a Reverse Reinforcement Learning (Reverse RL) approach for representing retrospective knowledge. General Value Functions (GVFs) have enjoyed great success in representing predictive knowledge, i.e., answering questions about possible future outcomes such as "how much fuel will be consumed in expectation if we drive from A to B?". GVFs, however, cannot answer questions like "how much fuel do we expect a car to have given it is at B at time $t$?". To answer this question, we need to know when that car had a full tank and how that car came to B. Since such questions emphasize the influ…
New York University（纽约大学）；Google AI Language（谷歌人工智能语言部门）
We propose a method to efficiently learn diverse strategies in reinforcement learning for query reformulation in the tasks of document retrieval and question answering. In the proposed framework an agent consists of multiple specialized sub-agents and a meta-agent that learns to aggregate the answers from sub-agents to produce a final answer. Sub-agents are trained on disjoint partitions of the training data, while the meta-agent is trained on the full training set. Our method makes learning faster, because it is highly parallelizable, and has better generalization performance than strong base…
Technical University of Munich（慕尼黑工业大学）；University of Vienna（维也纳大学）
We propose to use reinforcement learning to inform transformer-based contextualized link prediction models by providing paths that are most useful for predicting the correct answer. This is in contrast to previous approaches, that either used reinforcement learning (RL) to directly search for the answer, or based their prediction on limited or randomly selected context. Our experiments on WN18RR and FB15k-237 show that contextualized link prediction models consistently outperform RL-based answer search, and that additional improvements (of up to 13.5% MRR) can be gained by combining RL with a …
The outcome of Jacobian singular values regularization was studied for supervised learning problems. It also was shown that Jacobian conditioning regularization can help to avoid the ``mode-collapse'' problem in Generative Adversarial Networks. In this paper, we try to answer the following question: Can information about policy conditioning help to shape a more stable and general policy of reinforcement learning agents? To answer this question, we conduct a study of Jacobian conditioning behavior during policy optimization. To the best of our knowledge, this is the first work that research con…
We frame Question Answering (QA) as a Reinforcement Learning task, an approach that we call Active Question Answering. We propose an agent that sits between the user and a black box QA system and learns to reformulate questions to elicit the best possible answers. The agent probes the system with, potentially many, natural language reformulations of an initial question and aggregates the returned evidence to yield the best answer. The reformulation system is trained end-to-end to maximize answer quality using policy gradient. We evaluate on SearchQA, a dataset of complex questions extracted fr…
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
Value-function approximation methods that operate in batch mode have foundational importance to reinforcement learning (RL). Finite sample guarantees for these methods often crucially rely on two types of assumptions: (1) mild distribution shift, and (2) representation conditions that are stronger than realizability. However, the necessity ("why do we need them?") and the naturalness ("when do they hold?") of such assumptions have largely eluded the literature. In this paper, we revisit these assumptions and provide theoretical results towards answering the above questions, and make steps towa…
Gulf University for Science and Technology（海湾科技大学）
We present a probabilistic logic programming framework to reinforcement learning, by integrating reinforce-ment learning, in POMDP environments, with normal hybrid probabilistic logic programs with probabilistic answer set seman-tics, that is capable of representing domain-specific knowledge. We formally prove the correctness of our approach. We show that the complexity of finding a policy for a reinforcement learning problem in our approach is NP-complete. In addition, we show that any reinforcement learning problem can be encoded as a classical logic program with answer set semantics. We als…
Self-Harmony: Learning to Harmonize Self-Supervision and Self-Play in Test-Time Reinforcement Learning
The University of Tokyo（东京大学）；RIKEN Center for Advanced Intelligence Project（理化学研究所先进情报项目中心）；The Institute of Statistical Mathematics（统计数学研究所）；Google Research Australia（澳大利亚谷歌研究）
University of Massachusetts, Amherst（马萨诸塞大学阿默斯特分校）；Carnegie Mellon University（卡内基梅隆大学）；University of Texas at Austin（德克萨斯大学奥斯汀分校）；Amazon Web Services（亚马逊网络服务）
Knowledge bases (KB), both automatically and manually constructed, are often incomplete --- many valid facts can be inferred from the KB by synthesizing existing information. A popular approach to KB completion is to infer new relations by combinatory reasoning over the information found along other paths connecting a pair of entities. Given the enormous size of KBs and the exponential number of paths, previous path-based models have considered only the problem of predicting a missing relation given two entities or evaluating the truth of a proposed triple. Additionally, these methods have tra…
LODESTAR: Robust Entropy-Based Answer Selection in Retrieval-Augmented Generation for Question Answering -- Directing Frozen-LLM Entropy with a Reinforcement-Learned Prompt Polarizer under Misleading Passages
Answer selection (AS) is a critical subtask of the open-domain question answering (QA) problem. The present paper proposes a method called RLAS-BIABC for AS, which is established on attention mechanism-based long short-term memory (LSTM) and the bidirectional encoder representations from transformers (BERT) word embedding, enriched by an improved artificial bee colony (ABC) algorithm for pretraining and a reinforcement learning-based algorithm for training backpropagation (BP) algorithm. BERT can be comprised in downstream work and fine-tuned as a united task-specific architecture, and the pre…
Clemson University（克莱姆森大学）；Université de Montréal（蒙特利尔大学）；Accenture (United States)（埃森哲（美国））；Arizona State University（亚利桑那州立大学）；Northeastern University（东北大学）
Coupled Variational Reinforcement Learning for Language Model General Reasoning
Chinese Information Processing Laboratory, Institute of Software, Chinese Academy of Sciences（中国科学院软件研究所信息处理实验室）；University of Chinese Academy of Sciences（中国科学院大学）
Cash App Labs（Cash App实验室）；Lawrence Berkeley National Laboratory（劳伦斯伯克利国家实验室）
We convert the DeepMind Mathematics Dataset into a reinforcement learning environment by interpreting it as a program synthesis problem. Each action taken in the environment adds an operator or an input into a discrete compute graph. Graphs which compute correct answers yield positive reward, enabling the optimization of a policy to construct compute graphs conditioned on problem statements. Baseline models are trained using Double DQN on various subsets of problem types, demonstrating the capability to learn to correctly construct graphs despite the challenges of combinatorial explosion and n…
Knowledge Representation is important issue in reinforcement learning. In this paper, we bridge the gap between reinforcement learning and knowledge representation, by providing a rich knowledge representation framework, based on normal logic programs with answer set semantics, that is capable of solving model-free reinforcement learning problems for more complex do-mains and exploits the domain-specific knowledge. We prove the correctness of our approach. We show that the complexity of finding an offline and online policy for a model-free reinforcement learning problem in our approach is NP-c…
University of Illinois at Chicago（伊利诺伊大学芝加哥分校）；Amazon（亚马逊）；Huawei Technologies（华为技术）；Jilin University（吉林大学）
In real-world question-answering (QA) systems, ill-formed questions, such as wrong words, ill word order, and noisy expressions, are common and may prevent the QA systems from understanding and answering them accurately. In order to eliminate the effect of ill-formed questions, we approach the question refinement task and propose a unified model, QREFINE, to refine the ill-formed questions to well-formed question. The basic idea is to learn a Seq2Seq model to generate a new question from the original one. To improve the quality and retrieval performance of the generated questions, we make two …
ReCrit: Transition-Aware Reinforcement Learning for Scientific Critic Reasoning
Shanghai Jiao Tong University（上海交通大学）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；National University of Singapore（新加坡国立大学）；Chinese University of Hong Kong（香港中文大学）；University of Oxford（牛津大学）；Tsinghua University（清华大学）
PRISMA: Reinforcement Learning Guided Two-Stage Policy Optimization in Multi-Agent Architecture for Open-Domain Multi-Hop Question Answering
Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；The University of Western Australia（西澳大学）；Huazhong University of Science and Technology（华中科技大学）；Tsinghua University（清华大学）；Shanghai AI Laboratory（上海人工智能实验室）
On the effectiveness of reward functions in reinforcement learning for confidence calibration of large language models
School of Computing National University of Singapore（新加坡国立大学计算机学院）；Institute of Advanced Intelligence and Computing（高级智能与计算研究所）；Agency for Science, Technology and Research（科技研究局）；Department of Electrical & Computer Engineering（电气与计算机工程系）
Goal-conditioned reinforcement learning (GCRL), related to a set of complex RL problems, trains an agent to achieve different goals under particular scenarios. Compared to the standard RL solutions that learn a policy solely depending on the states or observations, GCRL additionally requires the agent to make decisions according to different goals. In this survey, we provide a comprehensive overview of the challenges and algorithms for GCRL. Firstly, we answer what the basic problems are studied in this field. Then, we explain how goals are represented and present how existing solutions are de…
School of Interactive Computing（交互式计算学院）；Georgia Institute of Technology（佐治亚理工学院）
Text-based adventure games provide a platform on which to explore reinforcement learning in the context of a combinatorial action space, such as natural language. We present a deep reinforcement learning architecture that represents the game state as a knowledge graph which is learned during exploration. This graph is used to prune the action space, enabling more efficient exploration. The question of which action to take can be reduced to a question-answering task, a form of transfer learning that pre-trains certain parts of our architecture. In experiments using the TextWorld framework, we s…
Facebook AI Research（Facebook人工智能研究院）；Georgia Institute of Technology（佐治亚理工学院）
We present a modular approach for learning policies for navigation over long planning horizons from language input. Our hierarchical policy operates at multiple timescales, where the higher-level master policy proposes subgoals to be executed by specialized sub-policies. Our choice of subgoals is compositional and semantic, i.e. they can be sequentially combined in arbitrary orderings, and assume human-interpretable descriptions (e.g. 'exit room', 'find kitchen', 'find refrigerator', etc.). We use imitation learning to warm-start policies at each level of the hierarchy, dramatically increasing…
School of Interactive Computing（交互计算学院）；Georgia Institute of Technology（佐治亚理工学院）
Text adventure games, in which players must make sense of the world through text descriptions and declare actions through text descriptions, provide a stepping stone toward grounding action in language. Prior work has demonstrated that using a knowledge graph as a state representation and question-answering to pre-train a deep Q-network facilitates faster control policy transfer. In this paper, we explore the use of knowledge graphs as a representation for domain knowledge transfer for training text-adventure playing reinforcement learning agents. Our methods are tested across multiple compute…
The Vanguard Group（先锋集团）；University of Toronto（多伦多大学）
Query reformulation aims to alter noisy or ambiguous text sequences into coherent ones closer to natural language questions. This is to prevent errors from propagating in a client-facing pipeline and promote better communication with users. Besides, it is crucial to maintain performance in downstream environments like question answering when rephrased queries are given as input. We show that under the previous framework (AQA), attempts to alter RL algorithms do not bring significant benefits to either reward acquisition or sequence fluency. Instead, we leverage a query-reformulating text-to-te…
AutoSearch: Adaptive Search Depth for Efficient Agentic RAG via Reinforcement Learning
SKL-MAIS, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所SKL-MAIS实验室）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；School of Advanced Interdisciplinary Sciences, University of Chinese Academy of Sciences（中国科学院大学交叉学科学院）；Meituan（美团）
University of Innsbruck（因斯布鲁克大学）；Warsaw University of Technology（华沙理工大学）；Leiden University（莱顿大学）
The study of Variational Quantum Eigensolvers (VQEs) has been in the spotlight in recent times as they may lead to real-world applications of near-term quantum devices. However, their performance depends on the structure of the used variational ansatz, which requires balancing the depth and expressivity of the corresponding circuit. In recent years, various methods for VQE structure optimization have been introduced but the capacities of machine learning to aid with this problem has not yet been fully investigated. In this work, we propose a reinforcement learning algorithm that autonomously e…
