← Back to all news
arXiv AI By Hoda Yamani, Henry Williams, Bruce A. MacDonald

Integrating Novelty and Surprise for Experience Prioritization and Exploration in Image-Based Reinforcement Learning

Read the original on arXiv AI →

The paper proposes Novelty and Surprise Prioritized Experience Replay (NSPER) for image-based reinforcement learning, combining novelty to highlight underrepresented states and surprise to reveal gaps in the agent’s knowledge. An extended version, NSPER+R, also uses these signals as intrinsic rewards to enhance both replay quality and exploration. Experiments on DeepMind Control Suite tasks demonstrate that NSPER and NSPER+R accelerate training and improve convergence compared to existing methods.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

Hugging Face Trending Papers
Aug 18

Integrating Novelty and Surprise for Experience Prioritization and Exploration in Image-Based Reinforcement Learning

The paper tackles sample efficiency in image-based reinforcement learning by combining novelty and surprise signals to prioritize experiences. It proposes Novelty and Surprise Prioritized Experience Replay (NSPER) and an extended version, NSPER+R, which also uses these signals as intrinsic rewards. Experiments on DeepMind Control Suite tasks demonstrate that both methods accelerate training and improve convergence compared to existing techniques.

agentsreinforcement-learning
More like this →
arXiv Machine Learning
Aug 19

Repetition as Reinforcement: Enhancing Sample Efficiency via Instant Episode Repetition in Reinforcement Learning

The paper proposes Instant Episode Repetition (IER), a method that immediately repeats action sequences from high‑reward episodes during training to boost sample efficiency. Unlike passive replay techniques, IER actively shapes data collection by re‑executing successful behaviors for a set number of subsequent episodes. Experiments on MuJoCo, the DeepMind Control Suite, and a robotic manipulation task show that IER improves learning performance over standard SAC, TD3, and self‑imitation baselines.

By Hoda Yamani, Yuning Xing, Koen van Rijnsoever, Bruce A. MacDonald, Henry Williams
agentsreinforcement-learningroboticsbenchmarks
More like this →
arXiv AI
Jun 2

Emergence of Exploration in Policy Gradient Reinforcement Learning via Retrying

arXiv:2606. 00151v1 Announce Type: cross Abstract: In reinforcement learning (RL), agents benefit from exploration only because they repeatedly encounter similar states: trying different actions can improve performance or reduce uncertainty; without such retries, a greedy policy is optimal.

By Soichiro Nishimori, Paavo Parmas, Sotetsu Koyamada, Tadashi Kozuno, Toshinori Kitamura, Shin Ishii, Yutaka Matsuo
agentsreinforcement-learningbenchmarks
More like this →