Search Results for "multi-objective optimization"

This is the official C++ source code repository of the Bullet Physics SDK: real-time collision detection and multi-physics simulation for VR, games, visual effects, robotics, machine learning etc. We are developing a new differentiable simulator for robotics learning, called Tiny Differentiable Simulator, or TDS. The simulator allows for hybrid simulation with neural networks. It allows different automatic differentiation backends, for forward and reverse mode gradients.

ELF (Extensive, Lightweight, and Flexible) is a high-performance platform for reinforcement learning research that unifies simulation, data collection, and distributed training. A C++ core provides fast environments and concurrent actors, while Python bindings expose simple APIs for agents, replay, and optimization loops. It supports both single-agent and multi-agent settings, with batched stepping and shared-memory queues that keep GPUs saturated during training. ELF introduced widely used reference systems, most notably ELF OpenGo, demonstrating at-scale self-play with strong analysis tooling and public checkpoints. Its design emphasizes reproducibility: deterministic seeds, logging, and evaluation harnesses make large-scale experiments trackable and comparable. ...

An online database and cross-platform, game-like client where gardeners/farmers (small or large scale) can log their actions and measurements (such as weather, yield, current plant size). Any user can then play it back visually, or play with the data and see a simulation inferred from the knowledge database, or calculate an optimal design within given constraints, inferred from the knowledge available at that time. This is both a tool for playing, in order to entertain and inspire...