Skip to main content
Back to top
Ctrl
+
K
navground_learning 0.3.pre documentation
Contents:
Introduction
Installation
Tutorials
Basics
Gymnasium
PettingZoo
TorchRL
Using a ML policy in Navground
Empty environment
Learn to follow a direction.
Learn to reach a pose
Corridor with obstacle
Scenario
Learning
Crossing
Training one agent among many agents
Performance of policies trained in single-agent environment
Training agents among peers
Performance of policies trained in multi-agent environment
Periodic Crossing
Uniform speeds
Different speeds
Exclusive crossing on a pad
Scenario
Model-based behaviors
Single ML agent meets Dummy agent
Continous actions
Discrete actions
Centralized policy trained with SAC
Distributed policy
Parallel SAC
Parallel PPO with discrete actions
BenchMARL
Distributed policy with communication
Parallel SAC
Parallel PPO with discrete actions and MLP
Distributed policy with comm, trained centrally
BenchMARL
Guides
How to extend
Reference
Types
Indices
Register
Configuration
Rewards functions
Single-agent Gymnasium Environment
Multi-agent Pettingzoo Environment
Wrappers
Policies
Imitation Learning
Evaluation
Saving and Loading
Onnx
Navground Components
Utils
Examples
.rst
.pdf
Guides
Guides
#
Contents:
How to extend