Bibliography (34):

  1. Dream to Control: Learning Behaviors by Latent Imagination

  2. DreamerV2: Mastering Atari with Discrete World Models

  3. https://danijar.com/project/dreamerv3/

  4. https://x.com/danijarh/status/1613161946223677441

  5. https://minecraft.fandom.com/wiki/Diamond

  6. The MineRL 2019 Competition on Sample Efficient Reinforcement Learning using Human Priors

  7. The MineRL 2020 Competition on Sample Efficient Reinforcement Learning using Human Priors

  8. Maximum a Posteriori Policy Optimization

  9. Deep DPG (DDPG): Continuous control with deep reinforcement learning

  10. DP4G: Distributed Distributional Deterministic Policy Gradients

  11. Model-Based Reinforcement Learning for Atari

  12. SPR: Data-Efficient Reinforcement Learning with Self-Predictive Representations

  13. IRIS: Transformers are Sample-Efficient World Models

  14. Playing Atari with Deep Reinforcement Learning

  15. Muesli: Combining Improvements in Policy Optimization

  16. Deep Exploration via Bootstrapped DQN

  17. Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor

  18. https://arxiv.org/abs/2107.09645

  19. Rainbow: Combining Improvements in Deep Reinforcement Learning

  20. Proximal Policy Optimization Algorithms

  21. Learning to Generalize with Object-centric Agents in the Open World Survival Game Crafter

  22. Improving Variational Inference with Inverse Autoregressive Flow

  23. https://arxiv.org/pdf/2301.04104.pdf#page=19&org=deepmind

  24. https://arxiv.org/pdf/2301.04104#page=18&org=deepmind

  25. https://arxiv.org/pdf/2301.04104#page=22&org=deepmind

  26. 2023-hafner-figure1-dreamerv3outperformsbaselinesinsampleefficiencyonmanytasks.png

  27. Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videos

  28. https://arxiv.org/pdf/2301.04104#page=23&org=deepmind