Efficient Exploration

144 papers with code • 0 benchmarks • 2 datasets

Efficient Exploration is one of the main obstacles in scaling up modern deep reinforcement learning algorithms. The main challenge in Efficient Exploration is the balance between exploiting current estimates, and gaining information about poorly understood states and actions.

Source: Randomized Value Functions via Multiplicative Normalizing Flows

Libraries

Use these libraries to find Efficient Exploration models and implementations
2 papers
24

Latest papers with no code

VDSC: Enhancing Exploration Timing with Value Discrepancy and State Counts

no code yet • 26 Mar 2024

While more sophisticated exploration strategies can excel in specific, often sparse reward environments, existing simpler approaches, such as $\epsilon$-greedy, persist in outperforming them across a broader spectrum of domains.

Explore until Confident: Efficient Exploration for Embodied Question Answering

no code yet • 23 Mar 2024

We consider the problem of Embodied Question Answering (EQA), which refers to settings where an embodied agent such as a robot needs to actively explore an environment to gather information until it is confident about the answer to a question.

Safe Reinforcement Learning for Constrained Markov Decision Processes with Stochastic Stopping Time

no code yet • 23 Mar 2024

In this paper, we present an online reinforcement learning algorithm for constrained Markov decision processes with a safety constraint.

Efficient exploration of high-Tc superconductors by a gradient-based composition design

no code yet • 20 Mar 2024

We propose a material design method via gradient-based optimization on compositions, overcoming the limitations of traditional methods: exhaustive database searches and conditional generation models.

Beyond Joint Demonstrations: Personalized Expert Guidance for Efficient Multi-Agent Reinforcement Learning

no code yet • 13 Mar 2024

Multi-Agent Reinforcement Learning (MARL) algorithms face the challenge of efficient exploration due to the exponential increase in the size of the joint state-action space.

Finding Waldo: Towards Efficient Exploration of NeRF Scene Spaces

no code yet • 7 Mar 2024

Neural Radiance Fields (NeRF) have quickly become the primary approach for 3D reconstruction and novel view synthesis in recent years due to their remarkable performance.

Vlearn: Off-Policy Learning with Efficient State-Value Function Estimation

no code yet • 7 Mar 2024

Existing off-policy reinforcement learning algorithms typically necessitate an explicit state-action-value function representation, which becomes problematic in high-dimensional action spaces.

Noisy Spiking Actor Network for Exploration

no code yet • 7 Mar 2024

As a general method for exploration in deep reinforcement learning (RL), NoisyNet can produce problem-specific exploration strategies.

A Natural Extension To Online Algorithms For Hybrid RL With Limited Coverage

no code yet • 7 Mar 2024

Hybrid Reinforcement Learning (RL), leveraging both online and offline data, has garnered recent interest, yet research on its provable benefits remains sparse.

ACE : Off-Policy Actor-Critic with Causality-Aware Entropy Regularization

no code yet • 22 Feb 2024

The varying significance of distinct primitive behaviors during the policy learning process has been overlooked by prior model-free RL algorithms.