Cooperative exploration for multi-agent deep reinforcement learning
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 …
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**
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 …
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
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 …
confidence bound (UCB) into the value function as a bonus. However, UCB is specified to …
Dynamic bottleneck for robust self-supervised exploration
Exploration methods based on pseudo-count of transitions or curiosity of dynamics have
achieved promising results in solving reinforcement learning with sparse rewards. However …
achieved promising results in solving reinforcement learning with sparse rewards. However …
Flip** coins to estimate pseudocounts for exploration in reinforcement learning
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 …
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
Exploration strategy plays an important role in reinforcement learning, especially in sparse-
reward tasks. In cooperative multi-agent reinforcement learning~(MARL), designing a …
reward tasks. In cooperative multi-agent reinforcement learning~(MARL), designing a …
Pretraining in deep reinforcement learning: A survey
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 …
deep learning. Various breakthroughs ranging from games to robotics have spurred the …