Cooperative exploration for multi-agent deep reinforcement learning

IJ Liu, U Jain, RA Yeh… - … conference on machine …, 2021 - proceedings.mlr.press
Exploration is critical for good results in deep reinforcement learning and has attracted much
attention. However, existing multi-agent deep reinforcement learning algorithms still use …

Exploit reward shifting in value-based deep-rl: Optimistic curiosity-based exploration and conservative exploitation via linear reward sha**

H Sun, L Han, R Yang, X Ma… - Advances in neural …, 2022 - proceedings.neurips.cc
In this work, we study the simple yet universally applicable case of reward sha** in value-
based Deep Reinforcement Learning (DRL). We show that reward shifting in the form of a …

Optimal conservative offline rl with general function approximation via augmented lagrangian

P Rashidinejad, H Zhu, K Yang, S Russell… - ar** and backward induction
C Bai, L Wang, L Han, J Hao, A Garg… - International …, 2021 - proceedings.mlr.press
One principled approach for provably efficient exploration is incorporating the upper
confidence bound (UCB) into the value function as a bonus. However, UCB is specified to …

Dynamic bottleneck for robust self-supervised exploration

C Bai, L Wang, L Han, A Garg, J Hao… - Advances in Neural …, 2021 - proceedings.neurips.cc
Exploration methods based on pseudo-count of transitions or curiosity of dynamics have
achieved promising results in solving reinforcement learning with sparse rewards. However …

Flip** coins to estimate pseudocounts for exploration in reinforcement learning

S Lobel, A Bagaria, G Konidaris - … Conference on Machine …, 2023 - proceedings.mlr.press
We propose a new method for count-based exploration in high-dimensional state spaces.
Unlike previous work which relies on density models, we show that counts can be derived by …

Two heads are better than one: a simple exploration framework for efficient multi-agent reinforcement learning

J Li, K Kuang, B Wang, X Li, F Wu… - Advances in Neural …, 2024 - proceedings.neurips.cc
Exploration strategy plays an important role in reinforcement learning, especially in sparse-
reward tasks. In cooperative multi-agent reinforcement learning~(MARL), designing a …

Pretraining in deep reinforcement learning: A survey

Z **e, Z Lin, J Li, S Li, D Ye - arxiv preprint arxiv:2211.03959, 2022 - arxiv.org
The past few years have seen rapid progress in combining reinforcement learning (RL) with
deep learning. Various breakthroughs ranging from games to robotics have spurred the …