pyRDDLGym-jax 1.2__py3-none-any.whl → 2.0__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
@@ -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] = []
@@ -1367,6 +1414,7 @@ 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']

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-1.2.dist-info → pyRDDLGym_jax-2.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: pyRDDLGym-jax
-Version: 1.2
+Version: 2.0
 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

{pyRDDLGym_jax-1.2.dist-info → pyRDDLGym_jax-2.0.dist-info}/RECORD

@@ -1,12 +1,12 @@
-pyRDDLGym_jax/__init__.py,sha256=LTT-ZpL6vrKdC5t0O71pJnk3zMhDf1eXkNmoLoIRupo,19
+pyRDDLGym_jax/__init__.py,sha256=TiPG4w8nN4AzPkhugwVvZkHmAgP955NltD4QRmBLhRU,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=oKs9js7xyIc9-bxQFZSQNBw9s1nWQlz4DjENwEgSojY,100672
-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=Rn-aIqfgfWqu45bvCfPb9tB8RIOBVdbj-pI-V3WS2Z8,89212
+pyRDDLGym_jax/core/logic.py,sha256=_A6eGYtLVU3pbLAezxJVB9bnClJoaFIa2mBIDdFrqoU,39655
+pyRDDLGym_jax/core/planner.py,sha256=4j56l7SL7F89g2QA4nOpyhODmY0DamvxYLfCMKxJNbQ,118593
+pyRDDLGym_jax/core/simulator.py,sha256=DnPL93WVCMZqtqMUoiJdfWcH9pEvNgGfDfO4NV0wIS0,9271
+pyRDDLGym_jax/core/tuning.py,sha256=RKKtDZp7unvfbhZEoaunZtcAn5xtzGYqXBB_Ij_Aapc,24205
+pyRDDLGym_jax/core/visualization.py,sha256=XtQL1A5dQIlfeUpte-r3lNVw-GNLxj2EYUNMz7AFOtc,70359
 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
@@ -16,8 +16,8 @@ pyRDDLGym_jax/examples/run_plan.py,sha256=v2AvwgIa4Ejr626vBOgWFJIQvay3IPKWno02zt
 pyRDDLGym_jax/examples/run_scipy.py,sha256=wvcpWCvdjvYHntO95a7JYfY2fuCMUTKnqjJikW0PnL4,2291
 pyRDDLGym_jax/examples/run_tune.py,sha256=zqrhvLR5PeWJv0NsRxDCzAPmvgPgz_1NrtM1xBy6ndU,3606
 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-1.2.dist-info/LICENSE,sha256=Y0Gi6H6mLOKN-oIKGZulQkoTJyPZeAaeuZu7FXH-meg,1095
-pyRDDLGym_jax-1.2.dist-info/METADATA,sha256=oWVOtC5AvAm2Xvdd507gXr3b6_aZLaH7LnOj6hADdgQ,15090
-pyRDDLGym_jax-1.2.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
-pyRDDLGym_jax-1.2.dist-info/entry_points.txt,sha256=Q--z9QzqDBz1xjswPZ87PU-pib-WPXx44hUWAFoBGBA,59
-pyRDDLGym_jax-1.2.dist-info/top_level.txt,sha256=n_oWkP_BoZK0VofvPKKmBZ3NPk86WFNvLhi1BktCbVQ,14
-pyRDDLGym_jax-1.2.dist-info/RECORD,,
+pyRDDLGym_jax-2.0.dist-info/LICENSE,sha256=Y0Gi6H6mLOKN-oIKGZulQkoTJyPZeAaeuZu7FXH-meg,1095
+pyRDDLGym_jax-2.0.dist-info/METADATA,sha256=ZYIe9c_Tar4WO8qQOvcUIJVMmZznPUBRaegS0DH2un8,15090
+pyRDDLGym_jax-2.0.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
+pyRDDLGym_jax-2.0.dist-info/entry_points.txt,sha256=Q--z9QzqDBz1xjswPZ87PU-pib-WPXx44hUWAFoBGBA,59
+pyRDDLGym_jax-2.0.dist-info/top_level.txt,sha256=n_oWkP_BoZK0VofvPKKmBZ3NPk86WFNvLhi1BktCbVQ,14
+pyRDDLGym_jax-2.0.dist-info/RECORD,,