paper-with-me

Papers

Natural Language Specification of Reinforcement Learning Policies through Differentiable Decision Trees

2021-01-18 · Pradyumna Tambwekar, Andrew Silva, Nakul Gopalan, Matthew Gombolay

Human-AI policy specification is a novel procedure we define in which humans can collaboratively warm-start a robot's reinforcement learning policy. This procedure is comprised of two steps; (1) Policy Specification, i.e. humans specifying the behavior they would like their companion robot to accomplish, and (2) Policy Optimization, i.e. the robot applying reinforcement learning to improve the initial policy. Existing approaches to enabling collaborative policy specification are often unintelligible black-box methods, and are not catered towards making the autonomous system accessible to a novice end-user. In this paper, we develop a novel collaborative framework to allow humans to initialize and interpret an autonomous agent's behavior. Through our framework, we enable humans to specify an initial behavior model via unstructured, natural language (NL), which we convert to lexical decision trees. Next, we leverage these translated specifications, to warm-start reinforcement learning and allow the agent to further optimize these potentially suboptimal policies. Our approach warm-starts an RL agent by utilizing non-expert natural language specifications without incurring the additional domain exploration costs. We validate our approach by showing that our model is able to produce >80% translation accuracy, and that policies initialized by a human can match the performance of relevant RL baselines in two domains.

📄 PDF Abstract BibTeX arXiv:2101.07140

Code (1)

eleurent/highway-env 공식 구현

Tasks

BIG-bench Machine Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

Co-learning Planning and Control Policies Constrained by Differentiable Logic Specifications

2023-03-02 · Zikang Xiong, Daniel Lawson, Joe Eappen, Ahmed H. Qureshi 외

Synthesizing planning and control policies in robotics is a fundamental task, further complicated by factors such as complex logic specifications and high-dimensional robot dynamics. This paper presents a novel reinforce…

Hierarchical Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)+1

Interactive Learning from Natural Language and Demonstrations using Signal Temporal Logic

2022-07-01 · Sara Mohammadinejad, Jesse Thomason, Jyotirmoy V. Deshmukh

Natural language is an intuitive way for humans to communicate tasks to a robot. While natural language (NL) is ambiguous, real world tasks and their safety requirements need to be communicated unambiguously. Signal Temp…

Formal LogicQ-LearningReinforcement Learning (RL)Semantic Parsing

Automating the Refinement of Reinforcement Learning Specifications

2025-11-30 · Tanmay Ambadkar, Đorđe Žikelić, Abhinav Verma arxiv

Logical specifications have been shown to help reinforcement learning algorithms in achieving complex tasks. However, when a task is under-specified, agents might fail to learn useful policies. In this work, we explore t…

Reinforcement Learning

Model-Free Reinforcement Learning for Symbolic Automata-encoded Objectives

2022-02-04 · Anand Balakrishnan, Stefan Jakšić, Edgar A. Aguilar, Dejan Ničković 외

Reinforcement learning (RL) is a popular approach for robotic path planning in uncertain environments. However, the control policies trained for an RL agent crucially depend on user-defined, state-based reward functions.…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Inverse Reinforcement Learning with Natural Language Goals

2020-08-16 · Li Zhou, Kevin Small

Humans generally use natural language to communicate task requirements to each other. Ideally, natural language should also be usable for communicating goals to autonomous machines (e.g., robots) to minimize friction in …

FrictionInstruction Followingreinforcement-learningReinforcement Learning+1