DreamerV2 reaches human-level performance on 55 Atari games by learning behaviors inside a separately trained discrete-latent world model.
Dopamine: A research framework for deep reinforcement learning
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
abstract
Deep reinforcement learning (deep RL) research has grown significantly in recent years. A number of software offerings now exist that provide stable, comprehensive implementations for benchmarking. At the same time, recent deep RL research has become more diverse in its goals. In this paper we introduce Dopamine, a new research framework for deep RL that aims to support some of that diversity. Dopamine is open-source, TensorFlow-based, and provides compact and reliable implementations of some state-of-the-art deep RL agents. We complement this offering with a taxonomy of the different research objectives in deep RL research. While by no means exhaustive, our analysis highlights the heterogeneity of research in the field, and the value of frameworks such as ours.
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
Dreamer learns to control from images by imagining and optimizing behaviors in a learned latent world model, outperforming prior methods on 20 visual tasks in data efficiency and final performance.
MINTO sets bootstrapped targets to the minimum of online and target network estimates, yielding faster stable value learning across online/offline RL and discrete/continuous actions.
Many batch RL algorithms underperform both online DQN and the behavioral policy on Atari; an adapted discrete-action BCQ outperforms the others tested.
RQIQN introduces a Wasserstein DRO-based correction to Bellman quantile targets that enlarges distributional spread without altering risk-neutral averages.
Gymnasium establishes a standardized API for RL environments to improve interoperability, reproducibility, and ease of development in reinforcement learning.
Survey unifies the definition of plasticity loss in DRL, taxonomizes over 50 mitigations, identifies evaluation gaps, and finds general regularization often outperforms domain-specific methods.
citing papers explorer
-
Mastering Atari with Discrete World Models
DreamerV2 reaches human-level performance on 55 Atari games by learning behaviors inside a separately trained discrete-latent world model.
-
Dream to Control: Learning Behaviors by Latent Imagination
Dreamer learns to control from images by imagining and optimizing behaviors in a learned latent world model, outperforming prior methods on 20 visual tasks in data efficiency and final performance.
-
Use the Online Network If You Can: Towards Fast and Stable Reinforcement Learning
MINTO sets bootstrapped targets to the minimum of online and target network estimates, yielding faster stable value learning across online/offline RL and discrete/continuous actions.
-
Benchmarking Batch Deep Reinforcement Learning Algorithms
Many batch RL algorithms underperform both online DQN and the behavioral policy on Atari; an adapted discrete-action BCQ outperforms the others tested.
-
Quantile Geometry Regularization for Distributional Reinforcement Learning
RQIQN introduces a Wasserstein DRO-based correction to Bellman quantile targets that enlarges distributional spread without altering risk-neutral averages.
-
Gymnasium: A Standard Interface for Reinforcement Learning Environments
Gymnasium establishes a standardized API for RL environments to improve interoperability, reproducibility, and ease of development in reinforcement learning.
-
Plasticity Loss in Deep Reinforcement Learning: A Survey
Survey unifies the definition of plasticity loss in DRL, taxonomizes over 50 mitigations, identifies evaluation gaps, and finds general regularization often outperforms domain-specific methods.