spitis/mrl

This is a modular RL code base for research. The intent is to enable surgical modifications by designing the base agent as a list of modules that all live inside the agent's global namespace (so they can all access each other directly by name). This means we can change the algorithm of a complex…

Principalele funcționalități ale spitis/mrl sunt: Reinforcement Learning Environments, Offline RL Implementations.

Alternativele open-source pentru spitis/mrl includ: siemens/industrialbenchmark — Industrial Benchmark. aviralkumar2907/bear — Update (07/17): We have released a cleaner implementation of BEAR on top of rlkit at:… aviralkumar2907/cql — Code for Conservative Q-Learning for Offline Reinforcement Learning (https://arxiv.org/abs/2006.04779). avisingh599/cog — This repository accompanies the following paper:. benelot/pybullet-gym — PyBullet Gymperium. aravindr93/mjrl — This package contains implementations of various RL algorithms for continuous control tasks simulated with MuJoCo.