An information-theoretic perspective on intrinsic motivation in reinforcement learning: A survey
The reinforcement learning (RL) research area is very active, with an important number of
new contributions, especially considering the emergent field of deep RL (DRL). However, a …
new contributions, especially considering the emergent field of deep RL (DRL). However, a …
Evolutionary reinforcement learning: A survey
Reinforcement learning (RL) is a machine learning approach that trains agents to maximize
cumulative rewards through interactions with environments. The integration of RL with deep …
cumulative rewards through interactions with environments. The integration of RL with deep …
Behavior from the void: Unsupervised active pre-training
We introduce a new unsupervised pre-training method for reinforcement learning called
APT, which stands for Active Pre-Training. APT learns behaviors and representations by …
APT, which stands for Active Pre-Training. APT learns behaviors and representations by …
State entropy maximization with random encoders for efficient exploration
Recent exploration methods have proven to be a recipe for improving sample-efficiency in
deep reinforcement learning (RL). However, efficient exploration in high-dimensional …
deep reinforcement learning (RL). However, efficient exploration in high-dimensional …
Exploration in deep reinforcement learning: From single-agent to multiagent domain
Deep reinforcement learning (DRL) and deep multiagent reinforcement learning (MARL)
have achieved significant success across a wide range of domains, including game artificial …
have achieved significant success across a wide range of domains, including game artificial …
Deep reinforcement learning versus evolution strategies: A comparative survey
AY Majid, S Saaybi, V Francois-Lavet… - … on Neural Networks …, 2023 - ieeexplore.ieee.org
Deep reinforcement learning (DRL) and evolution strategies (ESs) have surpassed human-
level control in many sequential decision-making problems, yet many open challenges still …
level control in many sequential decision-making problems, yet many open challenges still …
Accelerating reinforcement learning with value-conditional state entropy exploration
A promising technique for exploration is to maximize the entropy of visited state distribution,
ie, state entropy, by encouraging uniform coverage of visited state space. While it has been …
ie, state entropy, by encouraging uniform coverage of visited state space. While it has been …
Cem: Constrained entropy maximization for task-agnostic safe exploration
In the absence of assigned tasks, a learning agent typically seeks to explore its environment
efficiently. However, the pursuit of exploration will bring more safety risks. An under-explored …
efficiently. However, the pursuit of exploration will bring more safety risks. An under-explored …
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 …
Curiosity-driven exploration via latent bayesian surprise
The human intrinsic desire to pursue knowledge, also known as curiosity, is considered
essential in the process of skill acquisition. With the aid of artificial curiosity, we could equip …
essential in the process of skill acquisition. With the aid of artificial curiosity, we could equip …