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 …

Deep reinforcement learning at the edge of the statistical precipice

R Agarwal, M Schwarzer, PS Castro… - Advances in neural …, 2021‏ - proceedings.neurips.cc
Deep reinforcement learning (RL) algorithms are predominantly evaluated by comparing
their relative performance on a large suite of tasks. Most published results on deep RL …

Masked visual pre-training for motor control

T **ao, I Radosavovic, T Darrell, J Malik - arxiv preprint arxiv:2203.06173, 2022‏ - arxiv.org
This paper shows that self-supervised visual pre-training from real-world images is effective
for learning motor control tasks from pixels. We first train the visual representations by …

Mastering atari games with limited data

W Ye, S Liu, T Kurutach, P Abbeel… - Advances in neural …, 2021‏ - proceedings.neurips.cc
Reinforcement learning has achieved great success in many applications. However, sample
efficiency remains a key challenge, with prominent methods requiring millions (or even …

Mastering visual continuous control: Improved data-augmented reinforcement learning

D Yarats, R Fergus, A Lazaric, L Pinto - arxiv preprint arxiv:2107.09645, 2021‏ - arxiv.org
We present DrQ-v2, a model-free reinforcement learning (RL) algorithm for visual
continuous control. DrQ-v2 builds on DrQ, an off-policy actor-critic approach that uses data …

Curl: Contrastive unsupervised representations for reinforcement learning

M Laskin, A Srinivas, P Abbeel - International conference on …, 2020‏ - proceedings.mlr.press
Abstract We present CURL: Contrastive Unsupervised Representations for Reinforcement
Learning. CURL extracts high-level features from raw pixels using contrastive learning and …

Contrastive learning as goal-conditioned reinforcement learning

B Eysenbach, T Zhang, S Levine… - Advances in Neural …, 2022‏ - proceedings.neurips.cc
In reinforcement learning (RL), it is easier to solve a task if given a good representation.
While deep RL should automatically acquire such good representations, prior work often …

Image augmentation is all you need: Regularizing deep reinforcement learning from pixels

D Yarats, I Kostrikov, R Fergus - International conference on …, 2021‏ - openreview.net
We propose a simple data augmentation technique that can be applied to standard model-
free reinforcement learning algorithms, enabling robust learning directly from pixels without …