MORAL: Aligning AI with Human Norms through Multi-Objective Reinforced Active Learning

• URL: http://arxiv.org/abs/2201.00012v1
• Date: Thu, 30 Dec 2021 19:21:03 GMT
• Title: MORAL: Aligning AI with Human Norms through Multi-Objective Reinforced Active Learning
• Authors: Markus Peschl, Arkady Zgonnikov, Frans A. Oliehoek, Luciano C. Siebert
• Abstract summary: State-of-the art methods typically focus on learning a single reward model. We propose Multi-Objective Reinforced Active Learning (MORAL), a novel method for combining diverse demonstrations of social norms. Our approach is able to interactively tune a deep RL agent towards a variety of preferences, while eliminating the need for computing multiple policies.
• Score: 14.06682547001011
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Inferring reward functions from demonstrations and pairwise preferences are auspicious approaches for aligning Reinforcement Learning (RL) agents with human intentions. However, state-of-the art methods typically focus on learning a single reward model, thus rendering it difficult to trade off different reward functions from multiple experts. We propose Multi-Objective Reinforced Active Learning (MORAL), a novel method for combining diverse demonstrations of social norms into a Pareto-optimal policy. Through maintaining a distribution over scalarization weights, our approach is able to interactively tune a deep RL agent towards a variety of preferences, while eliminating the need for computing multiple policies. We empirically demonstrate the effectiveness of MORAL in two scenarios, which model a delivery and an emergency task that require an agent to act in the presence of normative conflicts. Overall, we consider our research a step towards multi-objective RL with learned rewards, bridging the gap between current reward learning and machine ethics literature.

Related papers

• From Novice to Expert: LLM Agent Policy Optimization via Step-wise Reinforcement Learning [62.54484062185869]
  We introduce StepAgent, which utilizes step-wise reward to optimize the agent's reinforcement learning process. We propose implicit-reward and inverse reinforcement learning techniques to facilitate agent reflection and policy adjustment.
  arXiv  Detail & Related papers  (2024-11-06T10:35:11Z)
• Unified Generative and Discriminative Training for Multi-modal Large Language Models [88.84491005030316]
  Generative training has enabled Vision-Language Models (VLMs) to tackle various complex tasks. Discriminative training, exemplified by models like CLIP, excels in zero-shot image-text classification and retrieval. This paper proposes a unified approach that integrates the strengths of both paradigms.
  arXiv  Detail & Related papers  (2024-11-01T01:51:31Z)
• DCIR: Dynamic Consistency Intrinsic Reward for Multi-Agent Reinforcement Learning [84.22561239481901]
  We propose a new approach that enables agents to learn whether their behaviors should be consistent with that of other agents. We evaluate DCIR in multiple environments including Multi-agent Particle, Google Research Football and StarCraft II Micromanagement.
  arXiv  Detail & Related papers  (2023-12-10T06:03:57Z)
• Learning in Cooperative Multiagent Systems Using Cognitive and Machine Models [1.0742675209112622]
  Multi-Agent Systems (MAS) are critical for many applications requiring collaboration and coordination with humans. One major challenge is the simultaneous learning and interaction of independent agents in dynamic environments. We propose three variants of Multi-Agent IBL models (MAIBL) We demonstrate that the MAIBL models exhibit faster learning and achieve better coordination in a dynamic CMOTP task with various settings of rewards compared to current MADRL models.
  arXiv  Detail & Related papers  (2023-08-18T00:39:06Z)
• Generating Personas for Games with Multimodal Adversarial Imitation Learning [47.70823327747952]
  Reinforcement learning has been widely successful in producing agents capable of playing games at a human level. Going beyond reinforcement learning is necessary to model a wide range of human playstyles. This paper presents a novel imitation learning approach to generate multiple persona policies for playtesting.
  arXiv  Detail & Related papers  (2023-08-15T06:58:19Z)
• Effective Multimodal Reinforcement Learning with Modality Alignment and Importance Enhancement [41.657470314421204]
  It is challenging to train an agent via reinforcement learning due to the heterogeneity and dynamic importance of different modalities. We propose a novel multimodal RL approach that can do multimodal alignment and importance enhancement according to their similarity and importance. We test our approach on several multimodal RL domains, showing that it outperforms state-of-the-art methods in terms of learning speed and policy quality.
  arXiv  Detail & Related papers  (2023-02-18T12:35:42Z)
• Imitation Learning from MPC for Quadrupedal Multi-Gait Control [63.617157490920505]
  We present a learning algorithm for training a single policy that imitates multiple gaits of a walking robot. We use and extend MPC-Net, which is an Imitation Learning approach guided by Model Predictive Control. We validate our approach on hardware and show that a single learned policy can replace its teacher to control multiple gaits.
  arXiv  Detail & Related papers  (2021-03-26T08:48:53Z)
• Opponent Learning Awareness and Modelling in Multi-Objective Normal Form Games [5.0238343960165155]
  It is essential for an agent to learn about the behaviour of other agents in the system. We present the first study of the effects of such opponent modelling on multi-objective multi-agent interactions with non-linear utilities.
  arXiv  Detail & Related papers  (2020-11-14T12:35:32Z)
• Scalable Multi-Agent Inverse Reinforcement Learning via Actor-Attention-Critic [54.2180984002807]
  Multi-agent adversarial inverse reinforcement learning (MA-AIRL) is a recent approach that applies single-agent AIRL to multi-agent problems. We propose a multi-agent inverse RL algorithm that is more sample-efficient and scalable than previous works.
  arXiv  Detail & Related papers  (2020-02-24T20:30:45Z)
• Ready Policy One: World Building Through Active Learning [35.358315617358976]
  We introduce Ready Policy One (RP1), a framework that views Model-Based Reinforcement Learning as an active learning problem. RP1 achieves this by utilizing a hybrid objective function, which crucially adapts during optimization. We rigorously evaluate our method on a variety of continuous control tasks, and demonstrate statistically significant gains over existing approaches.
  arXiv  Detail & Related papers  (2020-02-07T09:57:53Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.