agilerl 2.4.2.dev0__py3-none-any.whl → 2.4.3.dev0__py3-none-any.whl
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- agilerl/algorithms/core/base.py +1 -2
- agilerl/algorithms/ippo.py +1 -1
- agilerl/wrappers/agent.py +2 -2
- {agilerl-2.4.2.dev0.dist-info → agilerl-2.4.3.dev0.dist-info}/METADATA +2 -2
- {agilerl-2.4.2.dev0.dist-info → agilerl-2.4.3.dev0.dist-info}/RECORD +7 -7
- {agilerl-2.4.2.dev0.dist-info → agilerl-2.4.3.dev0.dist-info}/WHEEL +0 -0
- {agilerl-2.4.2.dev0.dist-info → agilerl-2.4.3.dev0.dist-info}/licenses/LICENSE +0 -0
agilerl/algorithms/core/base.py
CHANGED
|
@@ -2066,8 +2066,7 @@ class LLMAlgorithm(EvolvableAlgorithm, ABC):
|
|
|
2066
2066
|
accelerator: Optional[Accelerator] = None,
|
|
2067
2067
|
) -> None:
|
|
2068
2068
|
raise NotImplementedError(
|
|
2069
|
-
"The load class method is not supported for this algorithm class."
|
|
2070
|
-
"""
|
|
2069
|
+
"The load class method is not supported for this algorithm class." """
|
|
2071
2070
|
To load a saved LLM, please load the model as follows, and then re-instantiate the GRPO
|
|
2072
2071
|
class, using the pre-trained model.
|
|
2073
2072
|
|
agilerl/algorithms/ippo.py
CHANGED
|
@@ -671,7 +671,7 @@ class IPPO(MultiAgentRLAlgorithm):
|
|
|
671
671
|
:param action_space: Action space for the agent
|
|
672
672
|
:type action_space: gymnasium.spaces
|
|
673
673
|
"""
|
|
674
|
-
|
|
674
|
+
states, actions, log_probs, rewards, dones, values, next_state, next_done = (
|
|
675
675
|
experiences
|
|
676
676
|
)
|
|
677
677
|
|
agilerl/wrappers/agent.py
CHANGED
|
@@ -597,8 +597,8 @@ class AsyncAgentsWrapper(AgentWrapper[MultiAgentRLAlgorithm]):
|
|
|
597
597
|
:return: Learning information
|
|
598
598
|
:rtype: Any
|
|
599
599
|
"""
|
|
600
|
-
|
|
601
|
-
|
|
600
|
+
states, actions, log_probs, rewards, dones, values, next_state, next_done = map(
|
|
601
|
+
self.stack_experiences, experiences
|
|
602
602
|
)
|
|
603
603
|
|
|
604
604
|
# Handle case where we haven't collected a next state for each sub-agent
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
Metadata-Version: 2.4
|
|
2
2
|
Name: agilerl
|
|
3
|
-
Version: 2.4.
|
|
3
|
+
Version: 2.4.3.dev0
|
|
4
4
|
Summary: AgileRL is a deep reinforcement learning library focused on improving RL development through RLOps.
|
|
5
5
|
Author-email: Nick Ustaran-Anderegg <dev@agilerl.com>
|
|
6
6
|
License-Expression: Apache-2.0
|
|
@@ -22,7 +22,7 @@ Requires-Dist: omegaconf~=2.3.0
|
|
|
22
22
|
Requires-Dist: packaging>=20.0
|
|
23
23
|
Requires-Dist: pandas~=2.2.3
|
|
24
24
|
Requires-Dist: pettingzoo~=1.23.1
|
|
25
|
-
Requires-Dist: pre-commit~=3.
|
|
25
|
+
Requires-Dist: pre-commit~=3.8.0
|
|
26
26
|
Requires-Dist: pygame~=2.6.0
|
|
27
27
|
Requires-Dist: pymunk~=6.2.0
|
|
28
28
|
Requires-Dist: redis~=4.4.4
|
|
@@ -10,7 +10,7 @@ agilerl/algorithms/dqn.py,sha256=3WYga_sVDflP1xVUJ2u-24jcmC_a5F0EXfthDJ5fbpQ,162
|
|
|
10
10
|
agilerl/algorithms/dqn_rainbow.py,sha256=HyP-jkiVOkBUJmvpUlrB6VHo8m-AO2Z84M3Zb_ZP6fQ,20483
|
|
11
11
|
agilerl/algorithms/grpo.py,sha256=9VvRf4jQNDOfUlkKDZBNiiBACUybgeOxSQgnszjm2BM,19237
|
|
12
12
|
agilerl/algorithms/ilql.py,sha256=yQ6v6Y7n4JtsknCyhXOoJWMu-jbZX8CsLoitsEG2_YY,79849
|
|
13
|
-
agilerl/algorithms/ippo.py,sha256=
|
|
13
|
+
agilerl/algorithms/ippo.py,sha256=2JBPYnXGBxVbgkvy5BEa_m3Y4knKuIMA0EFNR3YADsQ,39083
|
|
14
14
|
agilerl/algorithms/maddpg.py,sha256=qVXDyb_W51lZtvst4K3yiosSy58BEBYbck8wF8CViBA,33908
|
|
15
15
|
agilerl/algorithms/matd3.py,sha256=n17y6PvM51r290Def_QeFT4p7TMo54MIDLN30XqlMk8,37926
|
|
16
16
|
agilerl/algorithms/neural_ts_bandit.py,sha256=jL_5mnExjMZdiIdwMWXT1XH-hWtaIiSokxi_n_qGTDY,11790
|
|
@@ -18,7 +18,7 @@ agilerl/algorithms/neural_ucb_bandit.py,sha256=wwo2sUNkIFtDDEOHIOp9aWhf5oeO9goi9
|
|
|
18
18
|
agilerl/algorithms/ppo.py,sha256=yAkgZT7WbZKn2oq62DFDPcfAmnRHomVPm4yNlI9-B-c,53025
|
|
19
19
|
agilerl/algorithms/td3.py,sha256=gFYlwwxYQgaWGDT5a-c3AOwI5WGQv4J4eeBotw1-fZY,23017
|
|
20
20
|
agilerl/algorithms/core/__init__.py,sha256=kKGnzj4TGRZKk2J6jcaKkK3s1LjCYu979o8u8OJUZjI,268
|
|
21
|
-
agilerl/algorithms/core/base.py,sha256=
|
|
21
|
+
agilerl/algorithms/core/base.py,sha256=R0GyAIC3CaRzNKkufU_omfKzpasGefxCFNq5yvvwQ78,122119
|
|
22
22
|
agilerl/algorithms/core/optimizer_wrapper.py,sha256=UQTlnv-mbNGlQ3RX9ocHtczXhTZq1MBKO6OdoQ879uM,13086
|
|
23
23
|
agilerl/algorithms/core/registry.py,sha256=ndaw9U814tHrPBhEPO9kLIDNKmLStTwLXPsnu-nnj8c,19991
|
|
24
24
|
agilerl/components/__init__.py,sha256=cc3bYeOdsNp-Puj_4_Ukj3kwmEqUqFeUo-5dZ3tP47o,292
|
|
@@ -84,12 +84,12 @@ agilerl/vector/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
|
84
84
|
agilerl/vector/pz_async_vec_env.py,sha256=uj9TyCn0SWksTUOW84RGspMkXqdGG-wjr86w08uCMb0,36742
|
|
85
85
|
agilerl/vector/pz_vec_env.py,sha256=sFVqm8eecxVHahTpFZEE3fvyZrmp2vMu0GECik8el6M,5978
|
|
86
86
|
agilerl/wrappers/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
87
|
-
agilerl/wrappers/agent.py,sha256=
|
|
87
|
+
agilerl/wrappers/agent.py,sha256=VyWju26YIfN4g8NCxTM-zMc3IGf5YKCXtyoeHynfEXE,23158
|
|
88
88
|
agilerl/wrappers/learning.py,sha256=nSVMg6eUBWn13NNdIFgCEHj31CaN_dGryQa13SmMvBw,2774
|
|
89
89
|
agilerl/wrappers/make_evolvable.py,sha256=sb9oAorGAayrD_6lNbyvHhefA_RKO4bSSNjqS6u9UhI,51079
|
|
90
90
|
agilerl/wrappers/pettingzoo_wrappers.py,sha256=Pw8VzabxfYCw5ad15y5J3rAH1teA6nVVo0RHCTTdOPQ,2063
|
|
91
91
|
agilerl/wrappers/utils.py,sha256=pENFH2AxsXd22s8HGUeM-jRowC0tmjHLWjqDwIq12l8,2194
|
|
92
|
-
agilerl-2.4.
|
|
93
|
-
agilerl-2.4.
|
|
94
|
-
agilerl-2.4.
|
|
95
|
-
agilerl-2.4.
|
|
92
|
+
agilerl-2.4.3.dev0.dist-info/METADATA,sha256=WgOdA0iK5157jv2Qtx_AlnCB0DdkMaHLF1b7Sc_Sxqo,20169
|
|
93
|
+
agilerl-2.4.3.dev0.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
|
|
94
|
+
agilerl-2.4.3.dev0.dist-info/licenses/LICENSE,sha256=vPX_VnIseflXJ30mQvwbXZoe208EtIr9ZVrl6cfdQNs,11720
|
|
95
|
+
agilerl-2.4.3.dev0.dist-info/RECORD,,
|
|
File without changes
|
|
File without changes
|