The Duality of Generative AI and Reinforcement Learning in Robotics: A Review

Fine-tuning language models from human preferences

Original

Ziegler, D.M., et al., 2019 · 1909

Earlier work this paper cites.

Learning to predict by the methods of temporal differences

Sutton, R.S., 1988 · 1988

Earlier work this paper cites.

Reinforcement learning: An introduction

Sutton, R., Barto, A., 1998 · 1998

Earlier work this paper cites.

D4rl: Datasets for deep data-driven reinforcement learning

Original

Fu, J., et al., 2020 · 2004

Earlier work this paper cites.

Efficient reductions for imitation learning, in: Teh, Y.W., Titterington, M. (Eds.), ICAIS, PMLR, Chia Laguna Resort, Sardinia, Italy. pp. 661–668

Ross, S., Bagnell, D., 2010 · 2010

Earlier work this paper cites.

Playing atari with deep reinforcement learning

Original

Mnih, V., et al., 2013 · 2013

Earlier work this paper cites.

Path planning with modified a star algorithm for a mobile robot

Duchoň, F., et al., 2014 · 2014

Earlier work this paper cites.

Human-level control through deep reinforcement learning

Mnih, V., et al., 2015 · 2015

Earlier work this paper cites.

Policy distillation

Original

Rusu, A.A., et al., 2015 · 2015

Earlier work this paper cites.

Generalized grounding graphs: A probabilistic framework for understanding grounded commands

Original

Kollar, T., et al., 2017 · 2017

Earlier work this paper cites.

Recurrent world models facilitate policy evolution

Ha, D., Schmidhuber, J., 2018 · 2018

Earlier work this paper cites.

Deterministic sampling-based motion planning: Optimality, complexity, and performance

Janson, L., et al., 2018 · 2018

Earlier work this paper cites.

Language as a cognitive tool to imagine goals in curiosity driven exploration

Colas, C., et al., 2020 · 2020

Earlier work this paper cites.

On the opportunities and risks of foundation models

Original

Bommasani, R., et al., 2021 · 2021

Earlier work this paper cites.

Classifier-free diffusion guidance, in: NeurIPS Workshop on Deep Generative Models and Downstream Applications

Ho, J., Salimans, T., 2021 · 2021

Earlier work this paper cites.

Learning transferable visual models from natural language supervision, in: ICML, Pmlr. pp. 8748–8763

Radford, A., et al., 2021 · 2021

Earlier work this paper cites.

Zero-shot text-to-image generation, in: ICML, Pmlr. pp. 8821–8831

Ramesh, A., et al., 2021 · 2021

Earlier work this paper cites.

A predictive safety filter for learning-based control of constrained nonlinear dynamical systems

Wabersich, K.P., Zeilinger, M.N., 2021 · 2021

Earlier work this paper cites.

Advances in preference-based reinforcement learning: A review, in: 2022 IEEE SMC, pp. 2527–2532

Abdelkareem, Y., et al., 2022 · 2022

Earlier work this paper cites.

Do as i can, not as i say: Grounding language in robotic affordances

Original

Ahn, M., et al., 2022 · 2022

Earlier work this paper cites.

Is conditional generative modeling all you need for decision-making?

Original

Ajay, A., et al., 2022 · 2022

Earlier work this paper cites.

Flamingo: a visual language model for few-shot learning

Alayrac, J.B., et al., 2022 · 2022

Earlier work this paper cites.

Rt-1: Robotics transformer for real-world control at scale

Original

Brohan, A., et al., 2022 · 2022

Earlier work this paper cites.

Offline reinforcement learning via high-fidelity generative behavior modeling

Original

Chen, H., et al., 2022 · 2022

Earlier work this paper cites.

Can foundation models perform zero-shot task specification for robot manipulation?, in: LDCC, PMLR. pp. 893–905

Cui, Y., et al., 2022 · 2022

Earlier work this paper cites.

A review of safe reinforcement learning: Methods, theory and applications

Original

Gu, S., et al., 2022 · 2022

Earlier work this paper cites.

Planning with diffusion for flexible behavior synthesis, in: ICML

Janner, M., et al., 2022 · 2022

Earlier work this paper cites.

Pre-training for robots: Offline rl enables learning new tasks in a handful of trials

Kumar, A., et al., 2022 · 2022

Earlier work this paper cites.

Vip: Towards universal visual reward and representation via value-implicit pre-training

Original

Ma, Y.J., et al., 2022 · 2022

Earlier work this paper cites.

Zero-shot reward specification via grounded natural language, in: ICML, PMLR. pp. 14743–14752

Mahmoudieh, P., et al., 2022 · 2022

Earlier work this paper cites.

Learning language-conditioned robot behavior from offline data and crowd-sourced annotation, in: CoRL, PMLR. pp. 1303–1315

Nair, S., et al., 2022 · 2022

Earlier work this paper cites.

A generalist agent

Original

Reed, S., et al., 2022 · 2022

Earlier work this paper cites.

High-resolution image synthesis with latent diffusion models, in: Proceedings of the IEEE/CVF, pp. 10684–10695

Rombach, R., et al., 2022 · 2022

Earlier work this paper cites.

Cliport: What and where pathways for robotic manipulation, in: CoRL, PMLR. pp. 894–906

Shridhar, M., et al., 2022 · 2022

Earlier work this paper cites.

Anymorph: Learning transferable polices by inferring agent morphology, in: ICML, PMLR. pp. 21677–21691

Trabucco, B., et al., 2022 · 2022

Earlier work this paper cites.

Diffusion policies as an expressive policy class for offline reinforcement learning

Original

Wang, Z., et al., 2022 · 2022

Earlier work this paper cites.

Multi-agent reinforcement learning is a sequence modeling problem

Wen, M., et al., 2022 · 2022

Earlier work this paper cites.

Socratic models: Composing zero-shot multimodal reasoning with language

Original

Zeng, A., et al., 2022 · 2022

Earlier work this paper cites.

A review of motion planning algorithms for intelligent robots

Zhou, C., et al., 2022 · 2022

Earlier work this paper cites.

Gpt-4 technical report

Original

Achiam, J., et al., 2023 · 2023

Earlier work this paper cites.

Language reward modulation for pretraining reinforcement learning

Original

Adeniji, A., et al., 2023 · 2023

Earlier work this paper cites.

Learning reward functions for robotic manipulation by observing humans, in: 2023 IEEE ICRA, IEEE. pp. 5006–5012

Alakuijala, M., et al., 2023 · 2023

Earlier work this paper cites.

Vision-language models as a source of rewards

Original

Baumli, K., et al., 2023 · 2023

Earlier work this paper cites.

A survey of meta-reinforcement learning

Original

Beck, J., et al., 2023 · 2023

Earlier work this paper cites.

Robotic offline rl from internet videos via value-function pre-training

Original

Bhateja, C., et al., 2023 · 2023

Earlier work this paper cites.

Pact: Perception-action causal transformer for autoregressive robotics pre-training, in: 2023 IEEE/RSJ IROS, IEEE. pp. 3621–3627

Bonatti, R., et al., 2023 · 2023

Cited alongside, same era.

Rt-2: Vision-language-action models transfer web knowledge to robotic control

Original

Brohan, A., et al., 2023 · 2023

Cited alongside, same era.

Latte: Language trajectory transformer, in: 2023 IEEE ICRA, IEEE. pp. 7287–7294

Bucker, A., et al., 2023 · 2023

Cited alongside, same era.

Grounding large language models in interactive environments with online reinforcement learning, in: ICML, PMLR. pp. 3676–3713

Carta, T., et al., 2023 · 2023

Cited alongside, same era.

Q-transformer: Scalable offline reinforcement learning via autoregressive q-functions, in: CoRL, PMLR. pp. 3909–3928

Chebotar, Y., et al., 2023 · 2023

Cited alongside, same era.

Survey on large language model-enhanced reinforcement learning: Concept, taxonomy, and methods

Original

Cao, Y., et al., 2024 · 2024

Closest in time.

Offline-to-online reinforcement learning for image-based grasping with scarce demonstrations, in: CoRL Workshop on Mastering Robot Manipulation in a World of Abundant Data

Chan, B., et al., 2024 · 2024

Closest in time.

A survey of robotic language grounding

Original

Cohen, V., et al., 2024 · 2024

Closest in time.

Plan-seq-learn: Language model guided rl for solving long horizon robotics tasks

Original

Dalal, M., et al., 2024 · 2024

Closest in time.

The llama 3 herd of models

Original