pyRDDLGym-jax 2.0__tar.gz → 2.2__tar.gz

{pyrddlgym_jax-2.0 → pyrddlgym_jax-2.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: pyRDDLGym-jax
-Version: 2.0
+Version: 2.2
 Summary: pyRDDLGym-jax: automatic differentiation for solving sequential planning problems in JAX.
 Home-page: https://github.com/pyrddlgym-project/pyRDDLGym-jax
 Author: Michael Gimelfarb, Ayal Taitler, Scott Sanner
@@ -58,18 +58,21 @@ Dynamic: summary
 
 Purpose:
 
-1. automatic translation of any RDDL description file into a differentiable simulator in JAX
-2. flexible policy class representations, automatic model relaxations for working in discrete and hybrid domains, and Bayesian hyper-parameter tuning.
+1. automatic translation of RDDL description files into differentiable JAX simulators
+2. implementation of (highly configurable) operator relaxations for working in discrete and hybrid domains
+3. flexible policy representations and automated Bayesian hyper-parameter tuning
+4. interactive dashboard for dyanmic visualization and debugging
+5. hybridization with parameter-exploring policy gradients.
 
 Some demos of solved problems by JaxPlan:
 
 <p align="middle">
-<img src="Images/intruders.gif" width="120" height="120" margin=0/>
-<img src="Images/marsrover.gif" width="120" height="120" margin=0/>
-<img src="Images/pong.gif" width="120" height="120" margin=0/>
-<img src="Images/quadcopter.gif" width="120" height="120" margin=0/>
-<img src="Images/reacher.gif" width="120" height="120" margin=0/>
-<img src="Images/reservoir.gif" width="120" height="120" margin=0/>
+<img src="https://github.com/pyrddlgym-project/pyRDDLGym-jax/blob/main/Images/intruders.gif" width="120" height="120" margin=0/>
+<img src="https://github.com/pyrddlgym-project/pyRDDLGym-jax/blob/main/Images/marsrover.gif" width="120" height="120" margin=0/>
+<img src="https://github.com/pyrddlgym-project/pyRDDLGym-jax/blob/main/Images/pong.gif" width="120" height="120" margin=0/>
+<img src="https://github.com/pyrddlgym-project/pyRDDLGym-jax/blob/main/Images/quadcopter.gif" width="120" height="120" margin=0/>
+<img src="https://github.com/pyrddlgym-project/pyRDDLGym-jax/blob/main/Images/reacher.gif" width="120" height="120" margin=0/>
+<img src="https://github.com/pyrddlgym-project/pyRDDLGym-jax/blob/main/Images/reservoir.gif" width="120" height="120" margin=0/>
 </p>
 
 > [!WARNING]  
@@ -219,7 +222,7 @@ Since version 1.0, JaxPlan has an optional dashboard that allows keeping track o
 and visualization of the policy or model, and other useful debugging features.
 
 <p align="middle">
-<img src="Images/dashboard.png" width="480" height="248" margin=0/>
+<img src="https://github.com/pyrddlgym-project/pyRDDLGym-jax/blob/main/Images/dashboard.png" width="480" height="248" margin=0/>
 </p>
 
 To run the dashboard, add the following entry to your config file:
@@ -235,8 +238,23 @@ More documentation about this and other new features will be coming soon.
 
 ## Tuning the Planner
 
-It is easy to tune the planner's hyper-parameters efficiently and automatically using Bayesian optimization.
-To do this, first create a config file template with patterns replacing concrete parameter values that you want to tune, e.g.:
+A basic run script is provided to run automatic Bayesian hyper-parameter tuning for the most sensitive parameters of JaxPlan:
+
+```shell
+jaxplan tune <domain> <instance> <method> <trials> <iters> <workers> <dashboard>
+```
+
+where:
+- ``domain`` is the domain identifier as specified in rddlrepository
+- ``instance`` is the instance identifier
+- ``method`` is the planning method to use (i.e. drp, slp, replan)
+- ``trials`` is the (optional) number of trials/episodes to average in evaluating each hyper-parameter setting
+- ``iters`` is the (optional) maximum number of iterations/evaluations of Bayesian optimization to perform
+- ``workers`` is the (optional) number of parallel evaluations to be done at each iteration, e.g. the total evaluations = ``iters * workers``
+- ``dashboard`` is whether the optimizations are tracked in the dashboard application.
+
+It is easy to tune a custom range of the planner's hyper-parameters efficiently. 
+First create a config file template with patterns replacing concrete parameter values that you want to tune, e.g.:
 
 ```ini
 [Model]
@@ -260,7 +278,7 @@ train_on_reset=True
 
 would allow to tune the sharpness of model relaxations, and the learning rate of the optimizer.
 
-Next, you must link the patterns in the config with concrete hyper-parameter ranges the tuner will understand:
+Next, you must link the patterns in the config with concrete hyper-parameter ranges the tuner will understand, and run the optimizer:
 
 ```python
 import pyRDDLGym
@@ -292,21 +310,7 @@ tuning = JaxParameterTuning(env=env,
                             gp_iters=iters)
 tuning.tune(key=42, log_file='path/to/log.csv')
 ```
- 
-A basic run script is provided to run the automatic hyper-parameter tuning for the most sensitive parameters of JaxPlan:
-
-```shell
-jaxplan tune <domain> <instance> <method> <trials> <iters> <workers>
-```
-
-where:
-- ``domain`` is the domain identifier as specified in rddlrepository
-- ``instance`` is the instance identifier
-- ``method`` is the planning method to use (i.e. drp, slp, replan)
-- ``trials`` is the (optional) number of trials/episodes to average in evaluating each hyper-parameter setting
-- ``iters`` is the (optional) maximum number of iterations/evaluations of Bayesian optimization to perform
-- ``workers`` is the (optional) number of parallel evaluations to be done at each iteration, e.g. the total evaluations = ``iters * workers``.
- 
+  
 
 ## Simulation
 
@@ -344,7 +348,16 @@ The [following citation](https://ojs.aaai.org/index.php/ICAPS/article/view/31480
 ```
 
 Some of the implementation details derive from the following literature, which you may wish to also cite in your research papers:
-- [A Distributional Framework for Risk-Sensitive End-to-End Planning in Continuous MDPs](https://ojs.aaai.org/index.php/AAAI/article/view/21226)
+- [A Distributional Framework for Risk-Sensitive End-to-End Planning in Continuous MDPs, AAAI 2022](https://ojs.aaai.org/index.php/AAAI/article/view/21226)
 - [Deep reactive policies for planning in stochastic nonlinear domains, AAAI 2019](https://ojs.aaai.org/index.php/AAAI/article/view/4744)
+- [Stochastic Planning with Lifted Symbolic Trajectory Optimization, AAAI 2019](https://ojs.aaai.org/index.php/ICAPS/article/view/3467/3335)
 - [Scalable planning with tensorflow for hybrid nonlinear domains, NeurIPS 2017](https://proceedings.neurips.cc/paper/2017/file/98b17f068d5d9b7668e19fb8ae470841-Paper.pdf)
-
+- [Baseline-Free Sampling in Parameter Exploring Policy Gradients: Super Symmetric PGPE, ANN 2015](https://link.springer.com/chapter/10.1007/978-3-319-09903-3_13)
+
+The model relaxations in JaxPlan are based on the following works:
+- [Poisson Variational Autoencoder, NeurIPS 2025](https://proceedings.neurips.cc/paper_files/paper/2024/file/4f3cb9576dc99d62b80726690453716f-Paper-Conference.pdf)
+- [Analyzing Differentiable Fuzzy Logic Operators, AI 2022](https://www.sciencedirect.com/science/article/pii/S0004370221001533)
+- [Learning with algorithmic supervision via continuous relaxations, NeurIPS 2021](https://proceedings.neurips.cc/paper_files/paper/2021/file/89ae0fe22c47d374bc9350ef99e01685-Paper.pdf)
+- [Universally quantized neural compression, NeurIPS 2020](https://papers.nips.cc/paper_files/paper/2020/file/92049debbe566ca5782a3045cf300a3c-Paper.pdf)
+- [Generalized Gumbel-Softmax Gradient Estimator for Generic Discrete Random Variables, 2020](https://arxiv.org/pdf/2003.01847)
+- [Categorical Reparametrization with Gumbel-Softmax, ICLR 2017](https://openreview.net/pdf?id=rkE3y85ee)

{pyrddlgym_jax-2.0 → pyrddlgym_jax-2.2}/README.md

@@ -12,18 +12,21 @@
 
 Purpose:
 
-1. automatic translation of any RDDL description file into a differentiable simulator in JAX
-2. flexible policy class representations, automatic model relaxations for working in discrete and hybrid domains, and Bayesian hyper-parameter tuning.
+1. automatic translation of RDDL description files into differentiable JAX simulators
+2. implementation of (highly configurable) operator relaxations for working in discrete and hybrid domains
+3. flexible policy representations and automated Bayesian hyper-parameter tuning
+4. interactive dashboard for dyanmic visualization and debugging
+5. hybridization with parameter-exploring policy gradients.
 
 Some demos of solved problems by JaxPlan:
 
 <p align="middle">
-<img src="Images/intruders.gif" width="120" height="120" margin=0/>
-<img src="Images/marsrover.gif" width="120" height="120" margin=0/>
-<img src="Images/pong.gif" width="120" height="120" margin=0/>
-<img src="Images/quadcopter.gif" width="120" height="120" margin=0/>
-<img src="Images/reacher.gif" width="120" height="120" margin=0/>
-<img src="Images/reservoir.gif" width="120" height="120" margin=0/>
+<img src="https://github.com/pyrddlgym-project/pyRDDLGym-jax/blob/main/Images/intruders.gif" width="120" height="120" margin=0/>
+<img src="https://github.com/pyrddlgym-project/pyRDDLGym-jax/blob/main/Images/marsrover.gif" width="120" height="120" margin=0/>
+<img src="https://github.com/pyrddlgym-project/pyRDDLGym-jax/blob/main/Images/pong.gif" width="120" height="120" margin=0/>
+<img src="https://github.com/pyrddlgym-project/pyRDDLGym-jax/blob/main/Images/quadcopter.gif" width="120" height="120" margin=0/>
+<img src="https://github.com/pyrddlgym-project/pyRDDLGym-jax/blob/main/Images/reacher.gif" width="120" height="120" margin=0/>
+<img src="https://github.com/pyrddlgym-project/pyRDDLGym-jax/blob/main/Images/reservoir.gif" width="120" height="120" margin=0/>
 </p>
 
 > [!WARNING]  
@@ -173,7 +176,7 @@ Since version 1.0, JaxPlan has an optional dashboard that allows keeping track o
 and visualization of the policy or model, and other useful debugging features.
 
 <p align="middle">
-<img src="Images/dashboard.png" width="480" height="248" margin=0/>
+<img src="https://github.com/pyrddlgym-project/pyRDDLGym-jax/blob/main/Images/dashboard.png" width="480" height="248" margin=0/>
 </p>
 
 To run the dashboard, add the following entry to your config file:
@@ -189,8 +192,23 @@ More documentation about this and other new features will be coming soon.
 
 ## Tuning the Planner
 
-It is easy to tune the planner's hyper-parameters efficiently and automatically using Bayesian optimization.
-To do this, first create a config file template with patterns replacing concrete parameter values that you want to tune, e.g.:
+A basic run script is provided to run automatic Bayesian hyper-parameter tuning for the most sensitive parameters of JaxPlan:
+
+```shell
+jaxplan tune <domain> <instance> <method> <trials> <iters> <workers> <dashboard>
+```
+
+where:
+- ``domain`` is the domain identifier as specified in rddlrepository
+- ``instance`` is the instance identifier
+- ``method`` is the planning method to use (i.e. drp, slp, replan)
+- ``trials`` is the (optional) number of trials/episodes to average in evaluating each hyper-parameter setting
+- ``iters`` is the (optional) maximum number of iterations/evaluations of Bayesian optimization to perform
+- ``workers`` is the (optional) number of parallel evaluations to be done at each iteration, e.g. the total evaluations = ``iters * workers``
+- ``dashboard`` is whether the optimizations are tracked in the dashboard application.
+
+It is easy to tune a custom range of the planner's hyper-parameters efficiently. 
+First create a config file template with patterns replacing concrete parameter values that you want to tune, e.g.:
 
 ```ini
 [Model]
@@ -214,7 +232,7 @@ train_on_reset=True
 
 would allow to tune the sharpness of model relaxations, and the learning rate of the optimizer.
 
-Next, you must link the patterns in the config with concrete hyper-parameter ranges the tuner will understand:
+Next, you must link the patterns in the config with concrete hyper-parameter ranges the tuner will understand, and run the optimizer:
 
 ```python
 import pyRDDLGym
@@ -246,21 +264,7 @@ tuning = JaxParameterTuning(env=env,
                             gp_iters=iters)
 tuning.tune(key=42, log_file='path/to/log.csv')
 ```
- 
-A basic run script is provided to run the automatic hyper-parameter tuning for the most sensitive parameters of JaxPlan:
-
-```shell
-jaxplan tune <domain> <instance> <method> <trials> <iters> <workers>
-```
-
-where:
-- ``domain`` is the domain identifier as specified in rddlrepository
-- ``instance`` is the instance identifier
-- ``method`` is the planning method to use (i.e. drp, slp, replan)
-- ``trials`` is the (optional) number of trials/episodes to average in evaluating each hyper-parameter setting
-- ``iters`` is the (optional) maximum number of iterations/evaluations of Bayesian optimization to perform
-- ``workers`` is the (optional) number of parallel evaluations to be done at each iteration, e.g. the total evaluations = ``iters * workers``.
- 
+  
 
 ## Simulation
 
@@ -298,7 +302,16 @@ The [following citation](https://ojs.aaai.org/index.php/ICAPS/article/view/31480
 ```
 
 Some of the implementation details derive from the following literature, which you may wish to also cite in your research papers:
-- [A Distributional Framework for Risk-Sensitive End-to-End Planning in Continuous MDPs](https://ojs.aaai.org/index.php/AAAI/article/view/21226)
+- [A Distributional Framework for Risk-Sensitive End-to-End Planning in Continuous MDPs, AAAI 2022](https://ojs.aaai.org/index.php/AAAI/article/view/21226)
 - [Deep reactive policies for planning in stochastic nonlinear domains, AAAI 2019](https://ojs.aaai.org/index.php/AAAI/article/view/4744)
+- [Stochastic Planning with Lifted Symbolic Trajectory Optimization, AAAI 2019](https://ojs.aaai.org/index.php/ICAPS/article/view/3467/3335)
 - [Scalable planning with tensorflow for hybrid nonlinear domains, NeurIPS 2017](https://proceedings.neurips.cc/paper/2017/file/98b17f068d5d9b7668e19fb8ae470841-Paper.pdf)
-
+- [Baseline-Free Sampling in Parameter Exploring Policy Gradients: Super Symmetric PGPE, ANN 2015](https://link.springer.com/chapter/10.1007/978-3-319-09903-3_13)
+
+The model relaxations in JaxPlan are based on the following works:
+- [Poisson Variational Autoencoder, NeurIPS 2025](https://proceedings.neurips.cc/paper_files/paper/2024/file/4f3cb9576dc99d62b80726690453716f-Paper-Conference.pdf)
+- [Analyzing Differentiable Fuzzy Logic Operators, AI 2022](https://www.sciencedirect.com/science/article/pii/S0004370221001533)
+- [Learning with algorithmic supervision via continuous relaxations, NeurIPS 2021](https://proceedings.neurips.cc/paper_files/paper/2021/file/89ae0fe22c47d374bc9350ef99e01685-Paper.pdf)
+- [Universally quantized neural compression, NeurIPS 2020](https://papers.nips.cc/paper_files/paper/2020/file/92049debbe566ca5782a3045cf300a3c-Paper.pdf)
+- [Generalized Gumbel-Softmax Gradient Estimator for Generic Discrete Random Variables, 2020](https://arxiv.org/pdf/2003.01847)
+- [Categorical Reparametrization with Gumbel-Softmax, ICLR 2017](https://openreview.net/pdf?id=rkE3y85ee)

pyrddlgym_jax-2.2/pyRDDLGym_jax/__init__.py

@@ -0,0 +1 @@
+__version__ = '2.2'