Skip to main content
Back to top
Ctrl
+
K
Purpose, benefits, license, and how to cite.
Install instructions for pip and git.
Beginner tutorial: initializing environments and policies, visualization, recording movies and logging.
Advanced tutorial: model inspection, compilation, grounding, debugging, and external functions.
Managing problems using rddlrepository.
Gradient-based simulation and planning with JaxPlan.
Planning by nonlinear programming with GurobiPlan.
Planning by Monte-Carlo Tree Search with PROST.
Reinforcement learning with stable-baselines3 and rllib.
Symbolic dynamic programming in RDDL domains.
Example gallery.
Simulating an environment in pyRDDLGym with a built-in policy.
Simulating an environment in pyRDDLGym with a custom policy.
Recording a movie of a simulation in pyRDDLGym.
Creating a Custom Visualizer in pyRDDLGym
Checking Constraints in pyRDDLGym
Modifying a Problem with pyRDDLGym
Grounding a problem in pyRDDLGym.
Extracting information from the compiled planning problem.
Analyzing fluent dependencies and evaluation order.
Calling External Functions in pyRDDLGym.
Loading a problem from the rddlrepository.
Adding domains to the rddlrepository.
Open-loop planning with straightline plans in JaxPlan.
Closed-loop planning with deep reactive policies in JaxPlan.
Closed-loop replanning with JaxPlan.
Monitoring progress with callbacks in JaxPlan.
Saving and loading trained policies in JaxPlan.
Building Custom Policies with JaxPlan
Building Structured RDDL Policies with JaxPlan
Tuning policy hyper-parameters in JaxPlan
Building an optimization problem for third-party optimizers.
Accelerating simulation with JAX.
Risk-aware planning with RAPTOR in JaxPlan.
Bayesian MDP Planning with JAX.
Partially-Observed Planning from Pixels with JaxPlan
Training a PPO policy with Stable Baselines 3.
Training a PPO policy with rllib.
Complete RDDL language specification.
Index
