pyRDDLGym-jax 1.3__py3-none-any.whl → 2.1__py3-none-any.whl

pyRDDLGym_jax/core/simulator.py

@@ -1,3 +1,23 @@
+# ***********************************************************************
+# JAXPLAN
+# 
+# Author: Michael Gimelfarb
+#
+# REFERENCES:
+# 
+# [1] Gimelfarb, Michael, Ayal Taitler, and Scott Sanner. "JaxPlan and GurobiPlan: 
+# Optimization Baselines for Replanning in Discrete and Mixed Discrete-Continuous 
+# Probabilistic Domains." Proceedings of the International Conference on Automated 
+# Planning and Scheduling. Vol. 34. 2024.
+# 
+# [2] Taitler, Ayal, Michael Gimelfarb, Jihwan Jeong, Sriram Gopalakrishnan, Martin 
+# Mladenov, Xiaotian Liu, and Scott Sanner. "pyRDDLGym: From RDDL to Gym Environments." 
+# In PRL Workshop Series {\textendash} Bridging the Gap Between AI Planning and 
+# Reinforcement Learning.
+#
+# ***********************************************************************
+
+
 import time
 from typing import Dict, Optional
 

pyRDDLGym_jax/core/tuning.py

@@ -1,3 +1,18 @@
+# ***********************************************************************
+# JAXPLAN
+# 
+# Author: Michael Gimelfarb
+#
+# REFERENCES:
+# 
+# [1] Gimelfarb, Michael, Ayal Taitler, and Scott Sanner. "JaxPlan and GurobiPlan: 
+# Optimization Baselines for Replanning in Discrete and Mixed Discrete-Continuous 
+# Probabilistic Domains." Proceedings of the International Conference on Automated 
+# Planning and Scheduling. Vol. 34. 2024.
+#
+# ***********************************************************************
+
+
 import csv
 import datetime
 import threading

pyRDDLGym_jax/core/visualization.py

@@ -1,3 +1,18 @@
+# ***********************************************************************
+# JAXPLAN
+# 
+# Author: Michael Gimelfarb
+#
+# REFERENCES:
+# 
+# [1] Gimelfarb, Michael, Ayal Taitler, and Scott Sanner. "JaxPlan and GurobiPlan: 
+# Optimization Baselines for Replanning in Discrete and Mixed Discrete-Continuous 
+# Probabilistic Domains." Proceedings of the International Conference on Automated 
+# Planning and Scheduling. Vol. 34. 2024.
+#
+# ***********************************************************************
+
+
 import ast
 import os
 from datetime import datetime
@@ -5,8 +20,7 @@ import math
 import numpy as np
 import time
 import threading
-from typing import Any, Dict, List, Optional, Tuple, TYPE_CHECKING
-import warnings
+from typing import Any, Dict, Optional, Tuple, TYPE_CHECKING
 import webbrowser
 
 # prevent endless console prints
@@ -17,7 +31,7 @@ log.setLevel(logging.ERROR)
 import dash
 from dash.dcc import Interval, Graph, Store
 from dash.dependencies import Input, Output, State, ALL
-from dash.html import Div, B, H4, P, Img, Hr
+from dash.html import Div, B, H4, P, Hr
 import dash_bootstrap_components as dbc
 
 import plotly.colors as pc 
@@ -38,6 +52,7 @@ REWARD_ERROR_DIST_SUBPLOTS = 20
 MODEL_STATE_ERROR_HEIGHT = 300
 POLICY_STATE_VIZ_MAX_HEIGHT = 800
 GP_POSTERIOR_MAX_HEIGHT = 800
+GP_POSTERIOR_PIXELS = 100
 
 PLOT_AXES_FONT_SIZE = 11
 EXPERIMENT_ENTRY_FONT_SIZE = 14
@@ -61,6 +76,7 @@ class JaxPlannerDashboard:
         self.xticks = {}
         self.test_return = {}
         self.train_return = {}
+        self.pgpe_return = {}
         self.return_dist = {}
         self.return_dist_ticks = {}
         self.return_dist_last_progress = {}
@@ -299,6 +315,9 @@ class JaxPlannerDashboard:
                                     dbc.Col(Graph(id='train-return-graph'), width=6),
                                     dbc.Col(Graph(id='test-return-graph'), width=6),
                                 ]),
+                                dbc.Row([                           
+                                    dbc.Col(Graph(id='pgpe-return-graph'), width=6)
+                                ]),
                                 dbc.Row([                           
                                     Graph(id='dist-return-graph')
                                 ])
@@ -661,6 +680,33 @@ class JaxPlannerDashboard:
             )
             return fig
         
+        @app.callback(
+            Output('pgpe-return-graph', 'figure'),
+            [Input('interval', 'n_intervals'),
+             Input('trigger-experiment-check', 'children'),
+             Input('tabs-main', 'active_tab')]
+        )
+        def update_pgpe_return_graph(n, trigger, active_tab):
+            if active_tab != 'tab-performance': return dash.no_update
+            fig = go.Figure()
+            for (row, checked) in self.checked.copy().items():
+                if checked:
+                    fig.add_trace(go.Scatter(
+                        x=self.xticks[row], y=self.pgpe_return[row],
+                        name=f'id={row}',
+                        mode='lines+markers',
+                        marker=dict(size=3), line=dict(width=2)
+                    ))
+            fig.update_layout(
+                title=dict(text="PGPE Return"),
+                xaxis=dict(title=dict(text="Training Iteration")),
+                yaxis=dict(title=dict(text="Cumulative Reward")),
+                font=dict(size=PLOT_AXES_FONT_SIZE),
+                legend=dict(bgcolor='rgba(0,0,0,0)'),
+                template="plotly_white"
+            )
+            return fig
+
         @app.callback(
             Output('dist-return-graph', 'figure'),
             [Input('interval', 'n_intervals'),
@@ -1316,6 +1362,7 @@ class JaxPlannerDashboard:
         self.xticks[experiment_id] = []
         self.train_return[experiment_id] = []
         self.test_return[experiment_id] = []
+        self.pgpe_return[experiment_id] = []
         self.return_dist_ticks[experiment_id] = []
         self.return_dist_last_progress[experiment_id] = 0
         self.return_dist[experiment_id] = []
@@ -1367,9 +1414,10 @@ class JaxPlannerDashboard:
         self.xticks[experiment_id].append(iteration)
         self.train_return[experiment_id].append(callback['train_return'])    
         self.test_return[experiment_id].append(callback['best_return'])
+        self.pgpe_return[experiment_id].append(callback['pgpe_return'])
         
         # data for return distributions
-        progress = callback['progress']
+        progress = int(callback['progress'])
         if progress - self.return_dist_last_progress[experiment_id] \
             >= PROGRESS_FOR_NEXT_RETURN_DIST:
             self.return_dist_ticks[experiment_id].append(iteration)
@@ -1438,8 +1486,8 @@ class JaxPlannerDashboard:
                 if i2 > i1:
                     
                     # Generate a grid for visualization
-                    p1_values = np.linspace(*bounds[param1], 100)
-                    p2_values = np.linspace(*bounds[param2], 100)
+                    p1_values = np.linspace(*bounds[param1], GP_POSTERIOR_PIXELS)
+                    p2_values = np.linspace(*bounds[param2], GP_POSTERIOR_PIXELS)
                     P1, P2 = np.meshgrid(p1_values, p2_values)
                     
                     # Predict the mean and deviation of the surrogate model
@@ -1452,8 +1500,7 @@ class JaxPlannerDashboard:
                     for p1, p2 in zip(np.ravel(P1), np.ravel(P2)):
                         params = {param1: p1, param2: p2}
                         params.update(fixed_params)
-                        param_grid.append(
-                            [params[key] for key in optimizer.space.keys])
+                        param_grid.append([params[key] for key in optimizer.space.keys])
                     param_grid = np.asarray(param_grid)
                     mean, std = optimizer._gp.predict(param_grid, return_std=True)
                     mean = mean.reshape(P1.shape)

pyRDDLGym_jax/examples/configs/Cartpole_Continuous_gym_replan.cfg

@@ -1,8 +1,8 @@
 [Model]
 logic='FuzzyLogic'
-comparison_kwargs={'weight': 50}
-rounding_kwargs={'weight': 50}
-control_kwargs={'weight': 50}
+comparison_kwargs={'weight': 20}
+rounding_kwargs={'weight': 20}
+control_kwargs={'weight': 20}
 
 [Optimizer]
 method='JaxStraightLinePlan'

pyRDDLGym_jax/examples/configs/Cartpole_Continuous_gym_slp.cfg

@@ -1,14 +1,14 @@
 [Model]
 logic='FuzzyLogic'
-comparison_kwargs={'weight': 30}
-rounding_kwargs={'weight': 30}
-control_kwargs={'weight': 30}
+comparison_kwargs={'weight': 20}
+rounding_kwargs={'weight': 20}
+control_kwargs={'weight': 20}
 
 [Optimizer]
 method='JaxStraightLinePlan'
 method_kwargs={}
 optimizer='rmsprop'
-optimizer_kwargs={'learning_rate': 0.002}
+optimizer_kwargs={'learning_rate': 0.001}
 batch_size_train=1
 batch_size_test=1
 clip_grad=1.0

pyRDDLGym_jax/examples/configs/Quadcopter_drp.cfg

@@ -11,6 +11,7 @@ optimizer='rmsprop'
 optimizer_kwargs={'learning_rate': 0.001}
 batch_size_train=1
 batch_size_test=1
+pgpe=None
 
 [Training]
 key=42

pyRDDLGym_jax/examples/configs/Quadcopter_slp.cfg

@@ -1,8 +1,8 @@
 [Model]
 logic='FuzzyLogic'
-comparison_kwargs={'weight': 50}
-rounding_kwargs={'weight': 50}
-control_kwargs={'weight': 50}
+comparison_kwargs={'weight': 10}
+rounding_kwargs={'weight': 10}
+control_kwargs={'weight': 10}
 
 [Optimizer]
 method='JaxStraightLinePlan'
@@ -11,6 +11,7 @@ optimizer='rmsprop'
 optimizer_kwargs={'learning_rate': 0.03}
 batch_size_train=1
 batch_size_test=1
+pgpe=None
 
 [Training]
 key=42

pyRDDLGym_jax/examples/configs/Reservoir_Continuous_drp.cfg

@@ -11,6 +11,7 @@ optimizer='rmsprop'
 optimizer_kwargs={'learning_rate': 0.0002}
 batch_size_train=32
 batch_size_test=32
+pgpe=None
 
 [Training]
 key=42

pyRDDLGym_jax/examples/configs/Reservoir_Continuous_slp.cfg

@@ -11,6 +11,7 @@ optimizer='rmsprop'
 optimizer_kwargs={'learning_rate': 0.2}
 batch_size_train=32
 batch_size_test=32
+pgpe=None
 
 [Training]
 key=42

pyRDDLGym_jax/examples/configs/UAV_Continuous_slp.cfg

@@ -11,6 +11,7 @@ optimizer='rmsprop'
 optimizer_kwargs={'learning_rate': 0.0003}
 batch_size_train=1
 batch_size_test=1
+pgpe=None
 
 [Training]
 key=42

pyRDDLGym_jax/examples/configs/Wildfire_MDP_ippc2014_drp.cfg

@@ -11,6 +11,7 @@ optimizer='rmsprop'
 optimizer_kwargs={'learning_rate': 0.001}
 batch_size_train=32
 batch_size_test=32
+pgpe=None
 
 [Training]
 key=42

pyRDDLGym_jax/examples/configs/Wildfire_MDP_ippc2014_replan.cfg

@@ -12,6 +12,7 @@ optimizer_kwargs={'learning_rate': 0.1}
 batch_size_train=32
 batch_size_test=32
 rollout_horizon=5
+pgpe=None
 
 [Training]
 key=42

pyRDDLGym_jax/examples/configs/Wildfire_MDP_ippc2014_slp.cfg

@@ -11,6 +11,7 @@ optimizer='rmsprop'
 optimizer_kwargs={'learning_rate': 0.01}
 batch_size_train=32
 batch_size_test=32
+pgpe=None
 
 [Training]
 key=42

pyRDDLGym_jax/examples/run_tune.py

@@ -3,7 +3,7 @@ is performed using a batched parallelized Bayesian optimization.
 
 The syntax is:
 
-    python run_tune.py <domain> <instance> <method> [<trials>] [<iters>] [<workers>]
+    python run_tune.py <domain> <instance> <method> [<trials>] [<iters>] [<workers>] [<dashboard>]
     
 where:
     <domain> is the name of a domain located in the /Examples directory
@@ -15,6 +15,7 @@ where:
     (defaults to 20)
     <workers> is the number of parallel workers (i.e. batch size), which must
     not exceed the number of cores available on the machine (defaults to 4)
+    <dashboard> is whether the dashboard is displayed
 '''
 import os
 import sys
@@ -35,7 +36,7 @@ def power_10(x):
     return 10.0 ** x
 
 
-def main(domain, instance, method, trials=5, iters=20, workers=4):
+def main(domain, instance, method, trials=5, iters=20, workers=4, dashboard=False):
     
     # set up the environment   
     env = pyRDDLGym.make(domain, instance, vectorized=True)
@@ -48,9 +49,9 @@ def main(domain, instance, method, trials=5, iters=20, workers=4):
     
     # map parameters in the config that will be tuned
     hyperparams = [
-        Hyperparameter('MODEL_WEIGHT_TUNE', -1., 5., power_10),
+        Hyperparameter('MODEL_WEIGHT_TUNE', -1., 4., power_10),
         Hyperparameter('POLICY_WEIGHT_TUNE', -2., 2., power_10),
-        Hyperparameter('LEARNING_RATE_TUNE', -5., 1., power_10),
+        Hyperparameter('LEARNING_RATE_TUNE', -5., 0., power_10),
         Hyperparameter('LAYER1_TUNE', 1, 8, power_2),
         Hyperparameter('LAYER2_TUNE', 1, 8, power_2),
         Hyperparameter('ROLLOUT_HORIZON_TUNE', 1, min(env.horizon, 100), int)       
@@ -64,7 +65,9 @@ def main(domain, instance, method, trials=5, iters=20, workers=4):
                                 eval_trials=trials,
                                 num_workers=workers,
                                 gp_iters=iters)
-    tuning.tune(key=42, log_file=f'gp_{method}_{domain}_{instance}.csv')
+    tuning.tune(key=42, 
+                log_file=f'gp_{method}_{domain}_{instance}.csv', 
+                show_dashboard=dashboard)
     
     # evaluate the agent on the best parameters
     planner_args, _, train_args = load_config_from_string(tuning.best_config)
@@ -77,7 +80,7 @@ def main(domain, instance, method, trials=5, iters=20, workers=4):
 
 def run_from_args(args):
     if len(args) < 3:
-        print('python run_tune.py <domain> <instance> <method> [<trials>] [<iters>] [<workers>]')
+        print('python run_tune.py <domain> <instance> <method> [<trials>] [<iters>] [<workers>] [<dashboard>]')
         exit(1)
     if args[2] not in ['drp', 'slp', 'replan']:
         print('<method> in [drp, slp, replan]')
@@ -86,6 +89,7 @@ def run_from_args(args):
     if len(args) >= 4: kwargs['trials'] = int(args[3])
     if len(args) >= 5: kwargs['iters'] = int(args[4])
     if len(args) >= 6: kwargs['workers'] = int(args[5])
+    if len(args) >= 7: kwargs['dashboard'] = bool(args[6])
     main(**kwargs) 
 
 

{pyRDDLGym_jax-1.3.dist-info → pyrddlgym_jax-2.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: pyRDDLGym-jax
-Version: 1.3
+Version: 2.1
 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
@@ -64,12 +64,12 @@ Purpose:
 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 +219,7 @@ 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:
@@ -296,7 +296,7 @@ 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>
+jaxplan tune <domain> <instance> <method> <trials> <iters> <workers> <dashboard>
 ```
 
 where:
@@ -305,7 +305,8 @@ where:
 - ``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``.
+- ``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.
  
 
 ## Simulation
@@ -344,7 +345,16 @@ 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-1.3.dist-info → pyrddlgym_jax-2.1.dist-info}/RECORD

@@ -1,12 +1,12 @@
-pyRDDLGym_jax/__init__.py,sha256=p_veRZMP15-djJyMuDHT7Ul1RbCCHpYsZ9LO0GD1URo,19
+pyRDDLGym_jax/__init__.py,sha256=iUkzbGTNPaXJsBuXc5YQfq1EDxnaYb9ZwmINbS0U8A8,19
 pyRDDLGym_jax/entry_point.py,sha256=dxDlO_5gneEEViwkLCg30Z-KVzUgdRXaKuFjoZklkA0,974
 pyRDDLGym_jax/core/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-pyRDDLGym_jax/core/compiler.py,sha256=qy1TSivdpuZxWecDl5HEM0PXX45JB7DHzV7uAB8kmbE,88696
-pyRDDLGym_jax/core/logic.py,sha256=iYvLgWyQd_mrkwwoeRWao9NzjmhsObQnPq4DphILw1Q,38425
-pyRDDLGym_jax/core/planner.py,sha256=TFFy91aCzRW600k_eP-7i2Gvp9wpNVjXlXtBnt9x03M,101744
-pyRDDLGym_jax/core/simulator.py,sha256=JpmwfPqYPBfEhmQ04ufBeclZOQ-U1ZiyAtLf1AIwO2M,8462
-pyRDDLGym_jax/core/tuning.py,sha256=LBhoVQZWWhYQj89gpM2B4xVHlYlKDt4psw4Be9cBbSY,23685
-pyRDDLGym_jax/core/visualization.py,sha256=uKhC8z0TeX9BklPNoxSVt0g5pkqhgxrQClQAih78ybY,68292
+pyRDDLGym_jax/core/compiler.py,sha256=_ERueJW7GQ7S8-IezreeuLs3fNCZbQZ8j7VMUVlEt1k,82306
+pyRDDLGym_jax/core/logic.py,sha256=ZeCwCLqC6BvXpRT06TvE2bfPNO6ALuMzPmUvXNzW6Uw,52278
+pyRDDLGym_jax/core/planner.py,sha256=N-vI52aN_vbOImwb8-hHCl3UxasPGX3gRi8w5bc6JiI,117922
+pyRDDLGym_jax/core/simulator.py,sha256=DnPL93WVCMZqtqMUoiJdfWcH9pEvNgGfDfO4NV0wIS0,9271
+pyRDDLGym_jax/core/tuning.py,sha256=RKKtDZp7unvfbhZEoaunZtcAn5xtzGYqXBB_Ij_Aapc,24205
+pyRDDLGym_jax/core/visualization.py,sha256=4BghMp8N7qtF0tdyDSqtxAxNfP9HPrQWTiXzAMJmx7o,70365
 pyRDDLGym_jax/core/assets/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 pyRDDLGym_jax/core/assets/favicon.ico,sha256=RMMrI9YvmF81TgYG7FO7UAre6WmYFkV3B2GmbA1l0kM,175085
 pyRDDLGym_jax/examples/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -14,10 +14,10 @@ pyRDDLGym_jax/examples/run_gradient.py,sha256=KhXvijRDZ4V7N8NOI2WV8ePGpPna5_vnET
 pyRDDLGym_jax/examples/run_gym.py,sha256=rXvNWkxe4jHllvbvU_EOMji_2-2k5d4tbBKhpMm_Gaw,1526
 pyRDDLGym_jax/examples/run_plan.py,sha256=v2AvwgIa4Ejr626vBOgWFJIQvay3IPKWno02ztIFCYc,2768
 pyRDDLGym_jax/examples/run_scipy.py,sha256=wvcpWCvdjvYHntO95a7JYfY2fuCMUTKnqjJikW0PnL4,2291
-pyRDDLGym_jax/examples/run_tune.py,sha256=zqrhvLR5PeWJv0NsRxDCzAPmvgPgz_1NrtM1xBy6ndU,3606
+pyRDDLGym_jax/examples/run_tune.py,sha256=WbGO8RudIK-cPMAMKvI8NbFQAqkG-Blbnta3Efsep6c,3828
 pyRDDLGym_jax/examples/configs/Cartpole_Continuous_gym_drp.cfg,sha256=mE8MqhOlkHeXIGEVrnR3QY6I-_iy4uxFYRA71P1bmtk,347
-pyRDDLGym_jax/examples/configs/Cartpole_Continuous_gym_replan.cfg,sha256=CI_c-E2Ij2dzVbYFA3sAUEXQBaIDImaEH15HpLqGQRw,370
-pyRDDLGym_jax/examples/configs/Cartpole_Continuous_gym_slp.cfg,sha256=T-O4faHYfSMyNNjY2jQ9XPK772szjbC7Enip5AaEO_0,340
+pyRDDLGym_jax/examples/configs/Cartpole_Continuous_gym_replan.cfg,sha256=nFFYHCKQUMn8x-OpJwu2pwe1tycNSJ8iAIwSkCBn33E,370
+pyRDDLGym_jax/examples/configs/Cartpole_Continuous_gym_slp.cfg,sha256=eJ3HvHjODoKdtX7u-AM51xQaHJnYgzEy2t3omNG2oCs,340
 pyRDDLGym_jax/examples/configs/HVAC_ippc2023_drp.cfg,sha256=9-QMZPZuecAEaerD79ZAbGX-tgfL8Y2W-tfkAyD15Cw,362
 pyRDDLGym_jax/examples/configs/HVAC_ippc2023_slp.cfg,sha256=BiY6wwSYkR9-T46AA4n3okJ1Qvj8Iu-y1V5BrfCbqrM,340
 pyRDDLGym_jax/examples/configs/MountainCar_Continuous_gym_slp.cfg,sha256=VBlTiHFQG72D1wpebMsuzSokwqlPVD99WjPp4YoWs84,356
@@ -25,15 +25,15 @@ pyRDDLGym_jax/examples/configs/MountainCar_ippc2023_slp.cfg,sha256=bH_5O13-Y6ztv
 pyRDDLGym_jax/examples/configs/PowerGen_Continuous_drp.cfg,sha256=Pq6E9RYksue7X2cWjdWyUsV0LqQTjTvq6p0aLBVKWfY,370
 pyRDDLGym_jax/examples/configs/PowerGen_Continuous_replan.cfg,sha256=SGVQAOqrOjEsZEtxL_Z6aGbLR19h5gKCcy0oz2vtQp8,382
 pyRDDLGym_jax/examples/configs/PowerGen_Continuous_slp.cfg,sha256=6obQik2FBldoJ3VwoVfGhQqKpKdnYox770cF-SGRi3Q,345
-pyRDDLGym_jax/examples/configs/Quadcopter_drp.cfg,sha256=Vvve7Os_bpmV0n-ZweW7JJAdWv16CZPyjHABqvST4_E,392
-pyRDDLGym_jax/examples/configs/Quadcopter_slp.cfg,sha256=ZxHmlddQhqNatXgv4A_i_972Mxo-eyGw4wdYmsTcvgU,345
-pyRDDLGym_jax/examples/configs/Reservoir_Continuous_drp.cfg,sha256=GXgQAmeciZeG3WCg1vFDVWMpjjc-rVja7CrJsJWuyN4,368
+pyRDDLGym_jax/examples/configs/Quadcopter_drp.cfg,sha256=rs-CzOAyZV_NvwSh2f6Fm9XNw5Z8WIYgpAOzgTm_Gv8,403
+pyRDDLGym_jax/examples/configs/Quadcopter_slp.cfg,sha256=EtSCTjd8gWm7akQdfHFxdpGnQvHzjo2IHbAuVxTAX4U,356
+pyRDDLGym_jax/examples/configs/Reservoir_Continuous_drp.cfg,sha256=7nPOJCo3eaZuq1pCyIJJJkDM0jjJThDuDECJDZzX-uc,379
 pyRDDLGym_jax/examples/configs/Reservoir_Continuous_replan.cfg,sha256=V3jzPGuNq2IAxYy_EeZWin4Y_uf0HvGhzg06ODNSY-I,381
-pyRDDLGym_jax/examples/configs/Reservoir_Continuous_slp.cfg,sha256=u8AZPm7vqBceWkXd6q_jNN6R70TTzf_BDS49BuVu91k,343
-pyRDDLGym_jax/examples/configs/UAV_Continuous_slp.cfg,sha256=0xktiJ6r_wWueW4BOU1CpCc_SgQ9U9l--OQMDaL7jIw,343
-pyRDDLGym_jax/examples/configs/Wildfire_MDP_ippc2014_drp.cfg,sha256=crCbQpeBm3Ab12wcpDG7SQmoLrNZsNIriFr0lhbdQ9o,371
-pyRDDLGym_jax/examples/configs/Wildfire_MDP_ippc2014_replan.cfg,sha256=HTQyW-zIIPyuE0zyrMngvjnjsJYiuG37NTCm7gBnPAA,440
-pyRDDLGym_jax/examples/configs/Wildfire_MDP_ippc2014_slp.cfg,sha256=mtZJh46OfEZYjMGw3V7EWzXJReXJNGulRrntj5cnRPk,402
+pyRDDLGym_jax/examples/configs/Reservoir_Continuous_slp.cfg,sha256=SYAJmoUIUhhvAej3XOzC5boGxKVHnSiVi5-ZGj2S29M,354
+pyRDDLGym_jax/examples/configs/UAV_Continuous_slp.cfg,sha256=osoIPfrldPw7oJF2AaAw0-ke6YHQNdrslFBCTytsqmo,354
+pyRDDLGym_jax/examples/configs/Wildfire_MDP_ippc2014_drp.cfg,sha256=oNX8uW8Bw2uG9zHX1zeLF3mHWDHRIlJXYvbFcY0pfCI,382
+pyRDDLGym_jax/examples/configs/Wildfire_MDP_ippc2014_replan.cfg,sha256=exCfGI3WU7IFO7n5rRe5cO1ZHAdFwttRYzjIdD4Pz2Y,451
+pyRDDLGym_jax/examples/configs/Wildfire_MDP_ippc2014_slp.cfg,sha256=e6Ikgv2uBbKuXHfVKt4KQ01LDUBGbc31D28bCcztJ58,413
 pyRDDLGym_jax/examples/configs/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 pyRDDLGym_jax/examples/configs/default_drp.cfg,sha256=XeMWAAG_OFZo7JAMxS5-XXroZaeVMzfM0NswmEobIns,373
 pyRDDLGym_jax/examples/configs/default_replan.cfg,sha256=CK4cEz8ReXyAZPLaLG9clIIRXAqM3IplUCxbLt_V2lY,407
@@ -41,9 +41,9 @@ pyRDDLGym_jax/examples/configs/default_slp.cfg,sha256=mJo0woDevhQCSQfJg30ULVy9qG
 pyRDDLGym_jax/examples/configs/tuning_drp.cfg,sha256=CQMpSCKTkGioO7U82mHMsYWFRsutULx0V6Wrl3YzV2U,504
 pyRDDLGym_jax/examples/configs/tuning_replan.cfg,sha256=m_0nozFg_GVld0tGv92Xao_KONFJDq_vtiJKt5isqI8,501
 pyRDDLGym_jax/examples/configs/tuning_slp.cfg,sha256=KHu8II6CA-h_HblwvWHylNRjSvvGS3VHxN7JQNR4p_Q,464
-pyRDDLGym_jax-1.3.dist-info/LICENSE,sha256=Y0Gi6H6mLOKN-oIKGZulQkoTJyPZeAaeuZu7FXH-meg,1095
-pyRDDLGym_jax-1.3.dist-info/METADATA,sha256=Colu-byYJ4RF5sr1qOVKg9VhCbrLnv32OvHt_A9KtLE,15090
-pyRDDLGym_jax-1.3.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
-pyRDDLGym_jax-1.3.dist-info/entry_points.txt,sha256=Q--z9QzqDBz1xjswPZ87PU-pib-WPXx44hUWAFoBGBA,59
-pyRDDLGym_jax-1.3.dist-info/top_level.txt,sha256=n_oWkP_BoZK0VofvPKKmBZ3NPk86WFNvLhi1BktCbVQ,14
-pyRDDLGym_jax-1.3.dist-info/RECORD,,
+pyrddlgym_jax-2.1.dist-info/LICENSE,sha256=Y0Gi6H6mLOKN-oIKGZulQkoTJyPZeAaeuZu7FXH-meg,1095
+pyrddlgym_jax-2.1.dist-info/METADATA,sha256=mVpp8qP4AnXEsjVCyCGjooSVZXn0y9zsbqLTm9qeMM4,16874
+pyrddlgym_jax-2.1.dist-info/WHEEL,sha256=jB7zZ3N9hIM9adW7qlTAyycLYW9npaWKLRzaoVcLKcM,91
+pyrddlgym_jax-2.1.dist-info/entry_points.txt,sha256=Q--z9QzqDBz1xjswPZ87PU-pib-WPXx44hUWAFoBGBA,59
+pyrddlgym_jax-2.1.dist-info/top_level.txt,sha256=n_oWkP_BoZK0VofvPKKmBZ3NPk86WFNvLhi1BktCbVQ,14
+pyrddlgym_jax-2.1.dist-info/RECORD,,

{pyRDDLGym_jax-1.3.dist-info → pyrddlgym_jax-2.1.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (75.8.0)
+Generator: setuptools (75.8.2)
 Root-Is-Purelib: true
 Tag: py3-none-any