A survey on offline reinforcement learning: Taxonomy, review, and open problems

RF Prudencio, MROA Maximo… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
With the widespread adoption of deep learning, reinforcement learning (RL) has
experienced a dramatic increase in popularity, scaling to previously intractable problems …

Reinforcement learning algorithms: A brief survey

AK Shakya, G Pillai, S Chakrabarty - Expert Systems with Applications, 2023 - Elsevier
Reinforcement Learning (RL) is a machine learning (ML) technique to learn sequential
decision-making in complex problems. RL is inspired by trial-and-error based human/animal …

Planning with diffusion for flexible behavior synthesis

M Janner, Y Du, JB Tenenbaum, S Levine - arXiv preprint arXiv …, 2022 - arxiv.org
Model-based reinforcement learning methods often use learning only for the purpose of
estimating an approximate dynamics model, offloading the rest of the decision-making work …

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

A Ajay, Y Du, A Gupta, J Tenenbaum… - arXiv preprint arXiv …, 2022 - arxiv.org
Recent improvements in conditional generative modeling have made it possible to generate
high-quality images from language descriptions alone. We investigate whether these …

Diffusion policies as an expressive policy class for offline reinforcement learning

Z Wang, JJ Hunt, M Zhou - arXiv preprint arXiv:2208.06193, 2022 - arxiv.org
Offline reinforcement learning (RL), which aims to learn an optimal policy using a previously
collected static dataset, is an important paradigm of RL. Standard RL methods often perform …

Decision transformer: Reinforcement learning via sequence modeling

L Chen, K Lu, A Rajeswaran, K Lee… - Advances in neural …, 2021 - proceedings.neurips.cc
We introduce a framework that abstracts Reinforcement Learning (RL) as a sequence
modeling problem. This allows us to draw upon the simplicity and scalability of the …

Offline reinforcement learning as one big sequence modeling problem

M Janner, Q Li, S Levine - Advances in neural information …, 2021 - proceedings.neurips.cc
Reinforcement learning (RL) is typically viewed as the problem of estimating single-step
policies (for model-free RL) or single-step models (for model-based RL), leveraging the …

Cal-ql: Calibrated offline rl pre-training for efficient online fine-tuning

M Nakamoto, S Zhai, A Singh… - Advances in …, 2024 - proceedings.neurips.cc
A compelling use case of offline reinforcement learning (RL) is to obtain a policy initialization
from existing datasets followed by fast online fine-tuning with limited interaction. However …

Uncertainty-based offline reinforcement learning with diversified q-ensemble

G An, S Moon, JH Kim… - Advances in neural …, 2021 - proceedings.neurips.cc
Offline reinforcement learning (offline RL), which aims to find an optimal policy from a
previously collected static dataset, bears algorithmic difficulties due to function …

Is pessimism provably efficient for offline rl?

Y Jin, Z Yang, Z Wang - International Conference on …, 2021 - proceedings.mlr.press
We study offline reinforcement learning (RL), which aims to learn an optimal policy based on
a dataset collected a priori. Due to the lack of further interactions with the environment …