TensorFlow Reinforcement Learning
The main features of deepmind/trfl are: Deep Learning Ecosystems, Deep Learning Frameworks, Machine Learning Frameworks, Reinforcement Learning, Research Platforms.
Open-source alternatives to deepmind/trfl include: tensorflow/agents — TF-Agents: A reliable, scalable and easy to use TensorFlow library for Contextual Bandits and Reinforcement Learning. keras-rl/keras-rl — keras-rl is a reinforcement learning library that enables the training of neural agents using Keras. It serves as a… batzner/tensorlm — Wrapper library for text generation / language models at character and word level with RNNs in TensorFlow. catalyst-team/catalyst — Accelerated deep learning R&D. autonomio/talos — Hyperparameter Experiments with TensorFlow and Keras. bsautermeister/tensorlight — TensorLight - A high-level framework for TensorFlow.
TF-Agents: A reliable, scalable and easy to use TensorFlow library for Contextual Bandits and Reinforcement Learning.
keras-rl is a reinforcement learning library that enables the training of neural agents using Keras. It serves as a framework for implementing deep reinforcement learning agents that interact with simulated environments to discover optimal behaviors and maximize cumulative rewards. The library provides a system for configuring, training, and managing neural network agents. It handles the interaction loop between agents and environments, allowing models to learn through direct experience and gradient-based optimization. The framework includes capabilities for model weight management, allowing
TensorLight - A high-level framework for TensorFlow
Hyperparameter Experiments with TensorFlow and Keras