Category: Synthetic

Using domain randomization, we repeatedly randomize the simulation dynamics during training. No. of environments: 1

Gym environment for Car Drifting. No. of environments: 3

Main purpose of this entire system is to investigate how human interaction can affect the traditional reinforcement learning framework No. of environments: 6

Discrete State-Action Abstraction. No. of environments: 751

Deep Transformer Q-Networks for Partially Observable Reinforcement Learning. No. of environments: 21

Eight Number environment in open ai gym style. No. of environments: 1

Evader is a reinforcement learning project where an agent learns to dodge falling objects using raycasts and policy gradients.. No. of environments: 1

A set of fishing environments for reinforcement learning, focused on sustainable fishery management and dynamic ecosystem modeling.. No. of environments: 10

Implementation of two OpenAI Gym environments for the Flappy Bird game.. No. of environments: 1

“2D match engine” of a football match using HTML Canvas. No. of environments: 4