Story Shaping: Teaching Agents Human-like Behavior with Stories

2023-01-24 · Xiangyu Peng, Christopher Cui, Wei Zhou, Renee Jia, Mark Riedl

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 from an exemplar story of how to accomplish a task and intrinsically rewards itself for performing actions that make its current environment adhere to that of the inferred story world. Specifically, Story Shaping infers a knowledge graph representation of the world state from observations, and also infers a knowledge graph from the exemplar story. An intrinsic reward is generated based on the similarity between the agent's inferred world state graph and the inferred story world graph. We conducted experiments in text-based games requiring commonsense reasoning and shaping the behaviors of agents as virtual game characters.

📄 PDF Abstract BibTeX arXiv:2301.10107

Code (0)

등록된 구현이 없습니다.

Tasks

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)text-based games

Methods 이 논문이 사용한 방법론

ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…

Agent-Agnostic Human-in-the-Loop Reinforcement Learning

2017-01-15 · David Abel, John Salvatier, Andreas Stuhlmüller, Owain Evans

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…

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Emotional Cost Functions for AI Safety: Teaching Agents to Feel the Weight of Irreversible Consequences

2026-03-15 · Pandurang Mopgar arxiv

Humans learn from catastrophic mistakes not through numerical penalties, but through qualitative suffering that reshapes who they are. Current AI safety approaches replicate none of this. Reward shaping captures magnitud…

A Reminder of its Brittleness: Language Reward Shaping May Hinder Learning for Instruction Following Agents

2023-05-26 · Sukai Huang, Nir Lipovetzky, Trevor Cohn

Teaching agents to follow complex written instructions has been an important yet elusive goal. One technique for enhancing learning efficiency is language reward shaping (LRS). Within a reinforcement learning (RL) framew…

Instruction Following Reinforcement Learning (RL)

Learning to Teach in Cooperative Multiagent Reinforcement Learning

2018-05-20 · Shayegan Omidshafiei, Dong-Ki Kim, Miao Liu, Gerald Tesauro 외

Collective human knowledge has clearly benefited from the fact that innovations by individuals are taught to others through communication. Similar to human social groups, agents in distributed learning systems would like…

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Dialogue Shaping: Empowering Agents through NPC Interaction

2023-07-28 · Wei Zhou, Xiangyu Peng, Mark Riedl

One major challenge in reinforcement learning (RL) is the large amount of steps for the RL agent needs to converge in the training process and learn the optimal policy, especially in text-based game environments where th…

Knowledge Graphs reinforcement-learning Reinforcement Learning (RL)