Reinforcement learning with prediction-based rewards

Learning Montezuma’s Revenge from a single demonstration

We’ve trained an agent to achieve a high score of 74,500 on Montezuma’s Revenge from a single human demonstration, better than any previously published result. Our algorithm is simple: the agent plays a sequence of games starting from carefully chosen states from the demonstration, and learns from them by optimizing the game score using PPO, the same reinforcement learning algorithm that underpins OpenAI Five.

Curiosity-Diffuser: Curiosity Guide Diffusion Models for Reliability

arXiv:2503. 14833v2 Announce Type: replace-cross Abstract: One of the bottlenecks in robotic intelligence is the instability of neural network models.

Curiosity-Critic: Cumulative Prediction Error Improvement as a Tractable Intrinsic Reward for World Model Training

arXiv:2604. 18701v3 Announce Type: replace-cross Abstract: Local prediction-error-based curiosity rewards focus on the current transition without considering the world model's cumulative prediction error across all visited transitions.

Improving Sample Efficiency in Multi-Agent Reinforcement Learning for Simulated Football Games via Exploration

arXiv:2503. 13077v2 Announce Type: replace Abstract: Multi-agent reinforcement learning has shown promise in learning cooperative behaviors in team-based environments.

Large-scale study of curiosity-driven learning

Efficient Exploration Is Enough

arXiv:2609.07575v1 Announce Type: cross Abstract: This work introduces an alternative view of efficient exploration and studies its theoretical and empirical implications in the absence of extrinsic...