Related papers: Switching Isotropic and Directional Exploration wi…
Deep reinforcement learning (RL) methods generally engage in exploratory behavior through noise injection in the action space. An alternative is to add noise directly to the agent's parameters, which can lead to more consistent exploration…
We introduce Random Reward Perturbation (RRP), a novel exploration strategy for reinforcement learning (RL). Our theoretical analyses demonstrate that adding zero-mean noise to environmental rewards effectively enhances policy diversity…
Numerous heuristics and advanced approaches have been proposed for exploration in different settings for deep reinforcement learning. Noise-based exploration generally fares well with dense-shaped rewards and bonus-based exploration with…
Efficient exploration remains a challenging research problem in reinforcement learning, especially when an environment contains large state spaces, deceptive local optima, or sparse rewards. To tackle this problem, we present a…
Exploration in complex domains is a key challenge in reinforcement learning, especially for tasks with very sparse rewards. Recent successes in deep reinforcement learning have been achieved mostly using simple heuristic exploration…
All reinforcement learning algorithms must handle the trade-off between exploration and exploitation. Many state-of-the-art deep reinforcement learning methods use noise in the action selection, such as Gaussian noise in policy gradient…
This paper reviews exploration techniques in deep reinforcement learning. Exploration techniques are of primary importance when solving sparse reward problems. In sparse reward problems, the reward is rare, which means that the agent will…
We introduce Random Latent Exploration (RLE), a simple yet effective exploration strategy in reinforcement learning (RL). On average, RLE outperforms noise-based methods, which perturb the agent's actions, and bonus-based exploration, which…
We propose a framework based on distributional reinforcement learning and recent attempts to combine Bayesian parameter updates with deep reinforcement learning. We show that our proposed framework conceptually unifies multiple previous…
This paper considers the task of performing binary search under noisy decisions, focusing on the application of target area localization. In the presence of noise, the classical partitioning approach of binary search is prone to error…
Exploration is a crucial and distinctive aspect of reinforcement learning (RL) that remains a fundamental open problem. Several methods have been proposed to tackle this challenge. Commonly used methods inject random noise directly into the…
A major challenge in reinforcement learning is exploration, when local dithering methods such as epsilon-greedy sampling are insufficient to solve a given task. Many recent methods have proposed to intrinsically motivate an agent to seek…
The objective of a reinforcement learning agent is to discover better actions through exploration. However, typical exploration techniques aim to maximize rewards, often incurring high costs in both exploration and learning processes. We…
Exploration is essential in reinforcement learning as an agent relies on trial and error to learn an optimal policy. However, when rewards are sparse, naive exploration strategies, like noise injection, are often insufficient. Intrinsic…
Recent developments have established the vulnerability of deep reinforcement learning to policy manipulation attacks via intentionally perturbed inputs, known as adversarial examples. In this work, we propose a technique for mitigation of…
Achieving efficient and scalable exploration in complex domains poses a major challenge in reinforcement learning. While Bayesian and PAC-MDP approaches to the exploration problem offer strong formal guarantees, they are often impractical…
When there exists an unlearnable source of randomness (noisy-TV) in the environment, a naively intrinsic reward driven exploring agent gets stuck at that source of randomness and fails at exploration. Intrinsic reward based on uncertainty…
Efficient exploration remains a major challenge for reinforcement learning. One reason is that the variability of the returns often depends on the current state and action, and is therefore heteroscedastic. Classical exploration strategies…
Bugs in popular distributed protocol implementations have been the source of many downtimes in popular internet services. We describe a randomized testing approach for distributed protocol implementations based on reinforcement learning.…
Reinforcement learning with sparse rewards is still an open challenge. Classic methods rely on getting feedback via extrinsic rewards to train the agent, and in situations where this occurs very rarely the agent learns slowly or cannot…