Improving Multimodal Interactive Agents with Reinforcement Learning from Human Feedback

• URL: http://arxiv.org/abs/2211.11602v1
• Date: Mon, 21 Nov 2022 16:00:31 GMT
• Title: Improving Multimodal Interactive Agents with Reinforcement Learning from Human Feedback
• Authors: Josh Abramson, Arun Ahuja, Federico Carnevale, Petko Georgiev, Alex Goldin, Alden Hung, Jessica Landon, Jirka Lhotka, Timothy Lillicrap, Alistair Muldal, George Powell, Adam Santoro, Guy Scully, Sanjana Srivastava, Tamara von Glehn, Greg Wayne, Nathaniel Wong, Chen Yan, Rui Zhu
• Abstract summary: An important goal in artificial intelligence is to create agents that can both interact naturally with humans and learn from their feedback. Here we demonstrate how to use reinforcement learning from human feedback to improve upon simulated, embodied agents.
• Score: 16.268581985382433
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: An important goal in artificial intelligence is to create agents that can both interact naturally with humans and learn from their feedback. Here we demonstrate how to use reinforcement learning from human feedback (RLHF) to improve upon simulated, embodied agents trained to a base level of competency with imitation learning. First, we collected data of humans interacting with agents in a simulated 3D world. We then asked annotators to record moments where they believed that agents either progressed toward or regressed from their human-instructed goal. Using this annotation data we leveraged a novel method - which we call "Inter-temporal Bradley-Terry" (IBT) modelling - to build a reward model that captures human judgments. Agents trained to optimise rewards delivered from IBT reward models improved with respect to all of our metrics, including subsequent human judgment during live interactions with agents. Altogether our results demonstrate how one can successfully leverage human judgments to improve agent behaviour, allowing us to use reinforcement learning in complex, embodied domains without programmatic reward functions. Videos of agent behaviour may be found at https://youtu.be/v_Z9F2_eKk4.

Related papers

• Learning to Influence Human Behavior with Offline Reinforcement Learning [70.7884839812069]
  We focus on influence in settings where there is a need to capture human suboptimality. Experiments online with humans is potentially unsafe, and creating a high-fidelity simulator of the environment is often impractical. We show that offline reinforcement learning can learn to effectively influence suboptimal humans by extending and combining elements of observed human-human behavior.
  arXiv  Detail & Related papers  (2023-03-03T23:41:55Z)
• Self-Improving Robots: End-to-End Autonomous Visuomotor Reinforcement Learning [54.636562516974884]
  In imitation and reinforcement learning, the cost of human supervision limits the amount of data that robots can be trained on. In this work, we propose MEDAL++, a novel design for self-improving robotic systems. The robot autonomously practices the task by learning to both do and undo the task, simultaneously inferring the reward function from the demonstrations.
  arXiv  Detail & Related papers  (2023-03-02T18:51:38Z)
• Creating Multimodal Interactive Agents with Imitation and Self-Supervised Learning [20.02604302565522]
  A common vision from science fiction is that robots will one day inhabit our physical spaces, sense the world as we do, assist our physical labours, and communicate with us through natural language. Here we study how to design artificial agents that can interact naturally with humans using the simplification of a virtual environment. We show that imitation learning of human-human interactions in a simulated world, in conjunction with self-supervised learning, is sufficient to produce a multimodal interactive agent, which we call MIA, that successfully interacts with non-adversarial humans 75% of the time.
  arXiv  Detail & Related papers  (2021-12-07T15:17:27Z)
• PEBBLE: Feedback-Efficient Interactive Reinforcement Learning via Relabeling Experience and Unsupervised Pre-training [94.87393610927812]
  We present an off-policy, interactive reinforcement learning algorithm that capitalizes on the strengths of both feedback and off-policy learning. We demonstrate that our approach is capable of learning tasks of higher complexity than previously considered by human-in-the-loop methods.
  arXiv  Detail & Related papers  (2021-06-09T14:10:50Z)
• Learning Human Rewards by Inferring Their Latent Intelligence Levels in Multi-Agent Games: A Theory-of-Mind Approach with Application to Driving Data [18.750834997334664]
  We argue that humans are bounded rational and have different intelligence levels when reasoning about others' decision-making process. We propose a new multi-agent Inverse Reinforcement Learning framework that reasons about humans' latent intelligence levels during learning.
  arXiv  Detail & Related papers  (2021-03-07T07:48:31Z)
• PsiPhi-Learning: Reinforcement Learning with Demonstrations using Successor Features and Inverse Temporal Difference Learning [102.36450942613091]
  We propose an inverse reinforcement learning algorithm, called emphinverse temporal difference learning (ITD) We show how to seamlessly integrate ITD with learning from online environment interactions, arriving at a novel algorithm for reinforcement learning with demonstrations, called $Psi Phi$-learning.
  arXiv  Detail & Related papers  (2021-02-24T21:12:09Z)
• Semi-supervised reward learning for offline reinforcement learning [71.6909757718301]
  Training agents usually requires reward functions, but rewards are seldom available in practice and their engineering is challenging and laborious. We propose semi-supervised learning algorithms that learn from limited annotations and incorporate unlabelled data. In our experiments with a simulated robotic arm, we greatly improve upon behavioural cloning and closely approach the performance achieved with ground truth rewards.
  arXiv  Detail & Related papers  (2020-12-12T20:06:15Z)
• Imitating Interactive Intelligence [24.95842455898523]
  We study how to design artificial agents that can interact naturally with humans using the simplification of a virtual environment. To build agents that can robustly interact with humans, we would ideally train them while they interact with humans. We use ideas from inverse reinforcement learning to reduce the disparities between human-human and agent-agent interactive behaviour.
  arXiv  Detail & Related papers  (2020-12-10T13:55:47Z)
• Accelerating Reinforcement Learning Agent with EEG-based Implicit Human Feedback [10.138798960466222]
  Reinforcement Learning (RL) agents with human feedback can dramatically improve various aspects of learning. Previous methods require human observer to give inputs explicitly, burdening the human in the loop of RL agent's learning process. We investigate capturing human's intrinsic reactions as implicit (and natural) feedback through EEG in the form of error-related potentials (ErrP)
  arXiv  Detail & Related papers  (2020-06-30T03:13:37Z)
• On the interaction between supervision and self-play in emergent communication [82.290338507106]
  We investigate the relationship between two categories of learning signals with the ultimate goal of improving sample efficiency. We find that first training agents via supervised learning on human data followed by self-play outperforms the converse.
  arXiv  Detail & Related papers  (2020-02-04T02:35:19Z)

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.