torchrl-nightly 2025.6.19__cp39-cp39-win_amd64.whl → 2025.6.21__cp39-cp39-win_amd64.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.
Files changed (30) hide show
  1. torchrl/_torchrl.cp39-win_amd64.pyd +0 -0
  2. torchrl/collectors/collectors.py +49 -24
  3. torchrl/collectors/llm/base.py +13 -6
  4. torchrl/collectors/llm/ray_collector.py +3 -0
  5. torchrl/data/__init__.py +2 -0
  6. torchrl/data/datasets/minari_data.py +1 -1
  7. torchrl/data/llm/__init__.py +2 -0
  8. torchrl/data/llm/chat.py +59 -9
  9. torchrl/data/llm/topk.py +186 -0
  10. torchrl/data/replay_buffers/ray_buffer.py +15 -1
  11. torchrl/data/replay_buffers/replay_buffers.py +50 -11
  12. torchrl/data/replay_buffers/samplers.py +98 -21
  13. torchrl/data/replay_buffers/storages.py +29 -2
  14. torchrl/envs/llm/__init__.py +2 -0
  15. torchrl/envs/llm/chat.py +4 -1
  16. torchrl/envs/llm/reward/gsm8k.py +15 -8
  17. torchrl/envs/llm/transforms/__init__.py +2 -1
  18. torchrl/envs/llm/transforms/kl.py +240 -4
  19. torchrl/envs/transforms/transforms.py +11 -27
  20. torchrl/modules/llm/policies/transformers_wrapper.py +71 -15
  21. torchrl/modules/llm/policies/vllm_wrapper.py +38 -5
  22. torchrl/objectives/llm/__init__.py +2 -1
  23. torchrl/objectives/llm/sft.py +465 -0
  24. torchrl/objectives/ppo.py +35 -12
  25. torchrl/version.py +2 -2
  26. {torchrl_nightly-2025.6.19.dist-info → torchrl_nightly-2025.6.21.dist-info}/METADATA +1 -1
  27. {torchrl_nightly-2025.6.19.dist-info → torchrl_nightly-2025.6.21.dist-info}/RECORD +30 -28
  28. {torchrl_nightly-2025.6.19.dist-info → torchrl_nightly-2025.6.21.dist-info}/LICENSE +0 -0
  29. {torchrl_nightly-2025.6.19.dist-info → torchrl_nightly-2025.6.21.dist-info}/WHEEL +0 -0
  30. {torchrl_nightly-2025.6.19.dist-info → torchrl_nightly-2025.6.21.dist-info}/top_level.txt +0 -0
@@ -3,11 +3,11 @@ build_tools/setup_helpers/__init__.py,sha256=l9zlK7Nm5bT7P_onQx-hZeIGzKKyCFm1PFk
3
3
  build_tools/setup_helpers/extension.py,sha256=ihV8jz8kqOvpqzuD006XqF1oNX5ukKGlwIOJRb1Vd-o,6075
4
4
  torchrl/__init__.py,sha256=76lKYwYKmAKORhyVt2tURmYAIRTifxxO3gWsskrHAXU,3054
5
5
  torchrl/_extension.py,sha256=x6Nqj2brF3VhlEwxmNA2fYbmpxq1HHGrHMnP0YnQwdc,2412
6
- torchrl/_torchrl.cp39-win_amd64.pyd,sha256=-x5ff7CzRafmHr8EUBuM1cp8BeUDxB_huWjPcpWX_Dk,449536
6
+ torchrl/_torchrl.cp39-win_amd64.pyd,sha256=bSVo0gBagJlHkSIJ08mrbCp2Chq95EDbktED_ZuNGZE,474112
7
7
  torchrl/_utils.py,sha256=2N35rdD65U1khMi5gVIz8-nMjlZsoVq0kCiQftVRSxw,42297
8
- torchrl/version.py,sha256=IG9KEp0S4wJWzGs9jZjDvNWWNpGGXYQDcTMyP_urorQ,85
8
+ torchrl/version.py,sha256=qrSt-wV9IZ8YXCgIg42ODdVhUj3c0MW9OPYRWulbkGY,85
9
9
  torchrl/collectors/__init__.py,sha256=LzTyfxmkNGPSa5-3rS5unQK7HfT5ZEdr2NV291rAOlU,832
10
- torchrl/collectors/collectors.py,sha256=ysm3IX-Ncmp8ZdhajqbZgP8jC_wy0xHel-KhoisA04A,180078
10
+ torchrl/collectors/collectors.py,sha256=Pz6VYYrekjBiVBQiyzp6zIyZrBdjSv4-FqlfrGYQz3E,181469
11
11
  torchrl/collectors/utils.py,sha256=aBmBLpphhfplqQjRCyn1jtWWJ-Wtc7TWvM0rOBN8SsE,11579
12
12
  torchrl/collectors/weight_update.py,sha256=Ydq5nJSTV3Q1uqLtJ_1Nj1JB5rwHwrG5StaLxymWFV4,21572
13
13
  torchrl/collectors/distributed/__init__.py,sha256=cKDWdNlwx2LoJkTwf-DKUXbq3Y-0Z1DctPYPcdgOSU0,730
@@ -18,12 +18,12 @@ torchrl/collectors/distributed/rpc.py,sha256=xta5tptC0mLlIY_AecLrARvFBYh7nMbclrr
18
18
  torchrl/collectors/distributed/sync.py,sha256=zjp0HEEcSMaDzq8xndoBWvyqYCdf7hp8urYRRiJP2GI,27912
19
19
  torchrl/collectors/distributed/utils.py,sha256=eY6M-vLCSzyACHRNBx5bHcieWsZfLg7DfNKGIv0IgHI,6625
20
20
  torchrl/collectors/llm/__init__.py,sha256=u03aQ97C3sb5-C0-s2tMBAGGs3kJTfZUSse29fHDkIk,365
21
- torchrl/collectors/llm/base.py,sha256=fs7YcEsGF8WtuS1my_4dyzAk94Yw4J25NnZxwnB7AzE,20842
22
- torchrl/collectors/llm/ray_collector.py,sha256=lxtHFkgmnMCNIUa9E3iDmpQfTs8tCuuZmydF6SJcnnM,11208
21
+ torchrl/collectors/llm/base.py,sha256=Wxdo4drsMk_i5u5DzDlikY4j5-TM9f6Ac4xjB6wJgPw,21132
22
+ torchrl/collectors/llm/ray_collector.py,sha256=nk-i61ZAsYkDNZW2Y7vcDhddjkUyyIuiDYjU9iWYklE,11364
23
23
  torchrl/collectors/llm/utils.py,sha256=GnDY2cTu4XEdwqqhFCP4QWfS2tsgaLTy8nwpIaTEsQI,1184
24
24
  torchrl/collectors/llm/weight_update/__init__.py,sha256=ngbL_sPfXh8FMM3r_j0B9QEP_jQIVSOa8pZVouHg9ec,281
25
25
  torchrl/collectors/llm/weight_update/vllm.py,sha256=4kRlEBHb6093d9lkKVIqU8ZwiPoCFtmVVaADuhxKLL4,11571
26
- torchrl/data/__init__.py,sha256=LEjVJd1OcHNz60lnoDMwoFtp-ejbqhWhhkydH_bgCfE,4974
26
+ torchrl/data/__init__.py,sha256=h6ZHGWzvWDfyw6tgo69gld5C_Kgg-T4DP-EVv1hy0Xk,5026
27
27
  torchrl/data/rlhf.py,sha256=_ENSvNe84snnFQG0jlTtOI419nIYtbBHvAw-pdFMiSs,1002
28
28
  torchrl/data/tensor_specs.py,sha256=PF-sta3dHy0UaDu26FS5-ZVlpAsagTUUMLmYHs5PQhk,254762
29
29
  torchrl/data/utils.py,sha256=tXBPxl5VHqPUfJF1VLqURmb066zDd9lipRDER4R1FY8,12444
@@ -33,18 +33,19 @@ torchrl/data/datasets/common.py,sha256=vusS4N4kUkplqmBPyJIQ2J8RDTO3TYFQULReSpkTe
33
33
  torchrl/data/datasets/d4rl.py,sha256=hHdvTRqXAp8sieglN9lwJYlmK2e6hVcmdrot8sZT0bo,20276
34
34
  torchrl/data/datasets/d4rl_infos.py,sha256=GYWrKvteI7wKYclBoggHpnvbMytfOTwhP3Gpr4TbMnA,22757
35
35
  torchrl/data/datasets/gen_dgrl.py,sha256=h8P-7yGTDjDNs5EYFCGK-EJyCZvFNCFfgEyY1xf_M28,14668
36
- torchrl/data/datasets/minari_data.py,sha256=gB7ermgKwg1UY81sPcg7wlopKv_qihUdexV0DG3OU4k,21185
36
+ torchrl/data/datasets/minari_data.py,sha256=0s8nfGJFnDTpelrZGZSnvKKhA-e6W2ki53wrjyMOwYE,21185
37
37
  torchrl/data/datasets/openml.py,sha256=hPSj9KXtn1_5GGbcfsrQhs5CM7aOfWCg4a0n_b5rTIA,7186
38
38
  torchrl/data/datasets/openx.py,sha256=0p2H3phnvsUgrFFfQulTyGEDcUrvXiFp-p18uFk8Xkk,34053
39
39
  torchrl/data/datasets/roboset.py,sha256=sLdDknyPj7f2NF5z5EbzEQ9QhD03VBKHEXXo_wxSRc4,17011
40
40
  torchrl/data/datasets/utils.py,sha256=tRZkarWl-BX_fnGEVNRt6Fjo0wmyKCNAuVmw5Le-0C4,350
41
41
  torchrl/data/datasets/vd4rl.py,sha256=YFjXvP-QGNzF7UWNKkGMKPFthcB0I8v6sJc7oESegYA,18694
42
- torchrl/data/llm/__init__.py,sha256=ZWoisCgT7JbAAHgcyrlp8o_q2mhgrgU4k-0kikLsTh8,941
43
- torchrl/data/llm/chat.py,sha256=fWvaGxsJY4qcohXtOUQdupJSOl4Jt-oSJuSyB-FqAEQ,31556
42
+ torchrl/data/llm/__init__.py,sha256=X86bYW_uNAwKJcxK2AVQpJo56tDejtXSDFtOyZMNhHQ,1006
43
+ torchrl/data/llm/chat.py,sha256=akIL6wj2QtpdWlFvOcRfPcrk7HE5NoSpgZxB8gtdOos,33962
44
44
  torchrl/data/llm/common.py,sha256=3Gb8sMojtNss6wi6hKGSIUDAwK1PC_8ve9W-bHCPjAk,2181
45
45
  torchrl/data/llm/dataset.py,sha256=GDuzflBq2ThgYn_V4bOr_1MHOhESnQ5jX1Wlcw69lfM,21194
46
46
  torchrl/data/llm/prompt.py,sha256=ikHWafhTIoCONCpuMHwIuGfpnPSpg5drZQTxTCmygQE,8578
47
47
  torchrl/data/llm/reward.py,sha256=QW1HWpNRORd3InwWLg-hAhjTlPqX4ffzAkYHEz0jQxo,8629
48
+ torchrl/data/llm/topk.py,sha256=4MTxYTTdfSBM5vxDHnleY7FatanzHgneXs8rjgKwwqQ,8539
48
49
  torchrl/data/llm/utils.py,sha256=K2NQoEhBC6VWowsMeDHu2Q8vbg3ZPEWBBN6z4qifiNM,24143
49
50
  torchrl/data/map/__init__.py,sha256=bON0vqCksU7FPoWNqiNcdl60t7yWUh9SdLhNtglj7jI,576
50
51
  torchrl/data/map/hash.py,sha256=XRYdaFHQUm87fL9pWjhvi2LeZVaqJsASkCU-G_Gus8s,7437
@@ -56,11 +57,11 @@ torchrl/data/postprocs/__init__.py,sha256=fOyX5OMaDb5HGrQbn9W72_QwncNdh6l3DkVSqR
56
57
  torchrl/data/postprocs/postprocs.py,sha256=dpXOKWlhdKy4Um7HdzRKe42PJ_Q1jHC7AX5plR9AIiw,15509
57
58
  torchrl/data/replay_buffers/__init__.py,sha256=oINoSWKO3Ku6YIBF-0KnbVLZwelZbANN4nLU4q6Mir0,2455
58
59
  torchrl/data/replay_buffers/checkpointers.py,sha256=eizAw4W0tQ2EWgfx6-EUV_3EuZMcZVdoahLoux15Nr4,15186
59
- torchrl/data/replay_buffers/ray_buffer.py,sha256=_8ZFBCJKgEcPWSjMoMGoJzUfN5eF9UD79dXK6Lh7dhc,9310
60
- torchrl/data/replay_buffers/replay_buffers.py,sha256=fO9SyUjNl-VUNch3FkwVKIRPkprAcypIcpbQpvCleUI,90708
61
- torchrl/data/replay_buffers/samplers.py,sha256=tBDi6GN2oe9WrJpnbqHmAAkNT0Du0Ce7Ldw9wWZ_7Jk,107888
60
+ torchrl/data/replay_buffers/ray_buffer.py,sha256=p8EkiXOP4EVMkkpjOyje7wiBfgbWOB0xhEJzDdelAxc,10135
61
+ torchrl/data/replay_buffers/replay_buffers.py,sha256=YzNV543zDpvENbUnqjjghkHHq6IwyRms1I3DXl-ayq4,92567
62
+ torchrl/data/replay_buffers/samplers.py,sha256=bFP8j3BahHULASAjeIGtxJX36GRsg3yBCNFu7vR6Zdo,112834
62
63
  torchrl/data/replay_buffers/scheduler.py,sha256=cGm4LZcZ2lo8azDMWKGTdhWApxjZFh0KfynApxAkVK4,10416
63
- torchrl/data/replay_buffers/storages.py,sha256=bP_pak6fi8X57OkXlQnbMX-ze7-VilRYKOTPr8KGkuA,61146
64
+ torchrl/data/replay_buffers/storages.py,sha256=VdEYOQ29FWGwDeHfLafZuobMlmuagxHVHnntKnU-yX4,62298
64
65
  torchrl/data/replay_buffers/utils.py,sha256=vlGfyHVKUAMKBR0l7fJM9NI47ZinS18Qzf8lpwoo6pI,39644
65
66
  torchrl/data/replay_buffers/writers.py,sha256=-aI6Y28oisuFDutMVlPp4e8wTe6x0wlY0MY1OUKHl4Q,28466
66
67
  torchrl/envs/__init__.py,sha256=2eVr8StUSMiNd-IoD5BQAFFuV10pAtO926b6QzRzB_M,6082
@@ -96,8 +97,8 @@ torchrl/envs/libs/smacv2.py,sha256=pr03oGHE2G_fc86qHeSQjSz3S6IH_l2hX0J2umb020M,2
96
97
  torchrl/envs/libs/unity_mlagents.py,sha256=vszCYjEX0S9AmIwLvGsoqc0Jr7jvlBAqZ1HQ1uqesjM,50558
97
98
  torchrl/envs/libs/utils.py,sha256=Ce8nAYc2MQOBTYCV17Yswk98pg3PStnaGPFVW2jqARQ,5354
98
99
  torchrl/envs/libs/vmas.py,sha256=giTORg2AqYzyjrazdD94fD2dNYwX7qe5TFnr-E1mjIg,37140
99
- torchrl/envs/llm/__init__.py,sha256=_srpJ1x42TqTbsMvJpTObVeyAlRhvG6XHpbRqk8qYi4,1274
100
- torchrl/envs/llm/chat.py,sha256=2ZN5fef0cYUGwLPHbDK3YNb9bI2pewIApQKzong-LKA,17993
100
+ torchrl/envs/llm/__init__.py,sha256=Iz5HtLoVy8O4u1mrPmyql4G8SU9S-MCinP_Gh8sbUWo,1320
101
+ torchrl/envs/llm/chat.py,sha256=YvADxo11RKkjD06rBvbbljch3Jb_H4snaBcgkU2Q-7w,18171
101
102
  torchrl/envs/llm/envs.py,sha256=wphbzLwDKYO_OTV63WYW4iTK5Ek4vmb1zNv5gehzodY,35450
102
103
  torchrl/envs/llm/datasets/__init__.py,sha256=6-x0WlKD7lpMVLKA4W1AktvgUs6adMuaGAqYYhgQ_hk,490
103
104
  torchrl/envs/llm/datasets/gsm8k.py,sha256=MfCFu0U7uetDtLdzUdvqX4rENXPsL8msnkMT98Q29jE,15624
@@ -105,18 +106,18 @@ torchrl/envs/llm/datasets/ifeval.py,sha256=sJ4bvXEWBzzNnDDbKkj6yz_1zemDStVFNfxqo
105
106
  torchrl/envs/llm/libs/__init__.py,sha256=zvUe6oe3pjZwGefV-_x4MAC6K89TMqxh3TZs5s3ADkI,274
106
107
  torchrl/envs/llm/libs/mlgym.py,sha256=TMaoV9P5w5EGgBSmLiw42_DOyKEh7ZGf3mDf-LaZ9W0,32237
107
108
  torchrl/envs/llm/reward/__init__.py,sha256=KYNJxyDOe2mZkjyH4CSuQ8qM0_Zu3EAaIGocYhLduPQ,380
108
- torchrl/envs/llm/reward/gsm8k.py,sha256=gkDQu0Xa8r4PEyuhH146M3dnlJbI7XAVzThIt3Opm1M,7899
109
+ torchrl/envs/llm/reward/gsm8k.py,sha256=TW2lACMLXHRlcTTRfTcFTLl7NIJA0TNh6qfSJiC52QI,8066
109
110
  torchrl/envs/llm/reward/ifeval/__init__.py,sha256=vvh7JSUQaEiMjNeMeJvWlcFb2-6_J1LfM6l4mENn4Zg,324
110
111
  torchrl/envs/llm/reward/ifeval/_instructions.py,sha256=jlNvIO3dykk8fBFXC35PQSDJ9vLF3knS-ywq2ILfF00,63362
111
112
  torchrl/envs/llm/reward/ifeval/_instructions_main.py,sha256=DEc7QqfujGxYvqcm2y_zPasBqB7FgSfXRt3QQ4HQUz0,4244
112
113
  torchrl/envs/llm/reward/ifeval/_instructions_registry.py,sha256=bY8R51RgjKJYiim67j5IXSfYhtWtvZrRF61yuqi0Tzs,3914
113
114
  torchrl/envs/llm/reward/ifeval/_instructions_util.py,sha256=63ZJbqUKaqMA_SDhnYT7VppULbible8udHGihiamxKc,27719
114
115
  torchrl/envs/llm/reward/ifeval/_scorer.py,sha256=iv-316dBYlz4fz6WUtzP7151y4xEwuwOq-Wf7Qazgmc,14928
115
- torchrl/envs/llm/transforms/__init__.py,sha256=P6-KVptxmsweLvwmnTl5dkfLS9JNAizwFPWOl8Hr3So,773
116
+ torchrl/envs/llm/transforms/__init__.py,sha256=BnVW7WVCYPlaNPd4cEyXIUI1Qfd7YQkZVsXvj5q5UVw,814
116
117
  torchrl/envs/llm/transforms/browser.py,sha256=d0JIUZ3TfgmqBcci5ihzzTqZA9KeTrs1iCProRWQQK8,10715
117
118
  torchrl/envs/llm/transforms/dataloading.py,sha256=Zl--I6bT2AqWDZmM6RMQq4ds3b1PFGqilAaIbXBJuNc,25054
118
119
  torchrl/envs/llm/transforms/format.py,sha256=tME390wkG0h2V5DAWHZa7EhJ5Or-6cga6AIjxPuy1l8,2592
119
- torchrl/envs/llm/transforms/kl.py,sha256=T-ab6P2PCpue0N4Pkz3ExttcEkTuPZylLlK5MGKAXuY,11992
120
+ torchrl/envs/llm/transforms/kl.py,sha256=GrANICxnF-FC_yVkdO4EU66bj7aTfkB8OXG7wA2uxDo,23251
120
121
  torchrl/envs/llm/transforms/policy_version.py,sha256=fko23hsQrAMmUqFwKjV_CQVavDhixXFUeVE0lJBASOA,7080
121
122
  torchrl/envs/llm/transforms/tokenizer.py,sha256=Nest15FD1iPLNZuw0rAobyb7n3ce6KFX00qfN3dUE2M,14274
122
123
  torchrl/envs/llm/transforms/tools.py,sha256=WoNgUN1Me4mhbqH5ef9XNc5qKXE0H-g3ZobjEKDM_kw,30308
@@ -130,7 +131,7 @@ torchrl/envs/transforms/llm.py,sha256=V2ZY8-QY27GCpGY5i0UrryohQclybyL7aZwU9glc7w
130
131
  torchrl/envs/transforms/r3m.py,sha256=3B-JB3GHh3s1Af69WZ3wl3BU8SP0g_QmuH8IPztXRbQ,13850
131
132
  torchrl/envs/transforms/rb_transforms.py,sha256=66zBM9RL_yYzIb4IKbLw9nDGtl_rHdMcOBn8fY7-1KY,7662
132
133
  torchrl/envs/transforms/rlhf.py,sha256=6PUb9SvF2cvyHUD_DmxQ4UM35VJ87qHit8PFHLWwLAk,653
133
- torchrl/envs/transforms/transforms.py,sha256=_YJYKybqeg8pp5PYWco9tQ-PedlOBDDv8_Gx5pEiQnM,491753
134
+ torchrl/envs/transforms/transforms.py,sha256=CXy3r1sETnY3azG7yoF-xV-gAxM-WChZlWPv0e4SWlU,491127
134
135
  torchrl/envs/transforms/utils.py,sha256=Arj9VR6_xP_Dzf0VMJNBwBZY4BDtEBg7nbK3Xlw9xsY,2128
135
136
  torchrl/envs/transforms/vc1.py,sha256=snXdONyRKkyMiaW-bT7SwDJUQVb5GWr1mqY1W78Ohn0,10841
136
137
  torchrl/envs/transforms/vecnorm.py,sha256=t3ho9ae_Mf-205FtneaWoaRP79AjCIsF7sdieD_vM0E,34863
@@ -147,8 +148,8 @@ torchrl/modules/llm/backends/__init__.py,sha256=ABKK4mJeRtoLXEqfnMvIuiovs7VJoCxn
147
148
  torchrl/modules/llm/backends/vllm.py,sha256=5P78jEtAIytgYHzEkOrg-wwqh1ryhiMVy4M_AxNQ9JQ,9649
148
149
  torchrl/modules/llm/policies/__init__.py,sha256=CK7VEdfShjkeNu_-TmYOobrCEjKTIb2aw2hE6s5RBNs,439
149
150
  torchrl/modules/llm/policies/common.py,sha256=GXzmVRa0SJvQ8iPMeuNjwV7EaZDOPrVy5k_LlJ10QXY,3111
150
- torchrl/modules/llm/policies/transformers_wrapper.py,sha256=yylsatdc63hodGcjhfO79CAA2-kQmuvRqiFT38mbPCQ,23177
151
- torchrl/modules/llm/policies/vllm_wrapper.py,sha256=iDG0593FfZfzf8-JiQQPANQ6O-WnF8ifQJw1-O4vDHs,30488
151
+ torchrl/modules/llm/policies/transformers_wrapper.py,sha256=0wDYGpC1T5T8ZVyZOi5S2Qoa2wtg5Oix2W9Y_bKMKs8,25988
152
+ torchrl/modules/llm/policies/vllm_wrapper.py,sha256=LBoFbrTyGiEiilYVmU7Ze-WBpwYinvAVIEtbU1QKajw,32226
152
153
  torchrl/modules/models/__init__.py,sha256=Y1XTkBOB5EMj6IaMru6V3CDwFLnkUtxzsHcqzeqq_4Y,1829
153
154
  torchrl/modules/models/batchrenorm.py,sha256=bR4ZhaJ5E1cSK5o8L2dNX5KVLIb-bgrYxcq6yhx0I1A,4869
154
155
  torchrl/modules/models/decision_transformer.py,sha256=ANFTOm3k9_3Uv1vKGdXumRy3meBPnDdT8HqhVvJ2RCo,6783
@@ -187,15 +188,16 @@ torchrl/objectives/dreamer.py,sha256=65EntKqou3auLMYxD1uaKGNyucfktabqaATNT1bExQc
187
188
  torchrl/objectives/functional.py,sha256=0Pr_debAMM2bp06HPGVIpLTcyBue4DvcyUJVsaa6AjE,2154
188
189
  torchrl/objectives/gail.py,sha256=ygwfF8MafJOIMxJ9mj_elhD2kwUMQQyqIhUN3arPqDI,9834
189
190
  torchrl/objectives/iql.py,sha256=VgCjfjKu91WCMCOK78vuc4k4kg1G3hPgOmjiKpozRM0,43976
190
- torchrl/objectives/ppo.py,sha256=_vvSLEMfT016Igk8ShQUP86yvMq0tXwXOotK2-egoHY,75334
191
+ torchrl/objectives/ppo.py,sha256=4GJVb8L_yhPnu_Jpwj5NzsOrPwXHT-DfskfOAWEtEmI,76846
191
192
  torchrl/objectives/redq.py,sha256=qRN5WyA6YHh7GcKX9n5GinXyETssAXJkiH0HuOx6Uss,29177
192
193
  torchrl/objectives/reinforce.py,sha256=EnUjqDSiTla3CuHg9rspQlvecd-VXZrPZxg4rGECZ8w,22861
193
194
  torchrl/objectives/sac.py,sha256=gKOgCU399miKgpgu7Bmzs1bkIF8JTm_lybHn8V4wDuk,65478
194
195
  torchrl/objectives/td3.py,sha256=Rq2q5gXo3AMuHm2OjRZvpfvKsAl1lIK5ALh2_sZM1ZE,23743
195
196
  torchrl/objectives/td3_bc.py,sha256=1pjB8mjCT2CLvQzjnqwAfZoc7yhjMB9UQjuJ5wZfTUY,26558
196
197
  torchrl/objectives/utils.py,sha256=Vrjj07SjMYANfFyn3n1xS7izBIs5Mq9mCvyITMzifZs,24705
197
- torchrl/objectives/llm/__init__.py,sha256=hlj2mKgz0BJR1ob1uObF8IkjyrDBnF24fXQf2zKEqaw,337
198
+ torchrl/objectives/llm/__init__.py,sha256=tZmIz3rkeclw3MzJoOWEs2gkewjx2USKrKJbWdyiiaQ,406
198
199
  torchrl/objectives/llm/grpo.py,sha256=nT3Ukjaz7nZZnkS5tnb-pDnRzvZ3L1edpcNCzi5WZRs,17164
200
+ torchrl/objectives/llm/sft.py,sha256=9fzX9Qo0Goyjxuwca6eLN1PUQ24F0LZGRpjzTDLFfs4,20572
199
201
  torchrl/objectives/multiagent/__init__.py,sha256=5uebDe5KrvlzeYV_BSd5vdmfruJQYMeDVVbU4iHErEg,245
200
202
  torchrl/objectives/multiagent/qmixer.py,sha256=yttOxc5FNylKw4iMnYSG1qO8EbHvx8imAhxNxW9_iLw,17362
201
203
  torchrl/objectives/value/__init__.py,sha256=QkSnenYVqe_3FVtwGr_D86N52unnpBvRXfcC5JFTBOw,589
@@ -221,8 +223,8 @@ torchrl/trainers/helpers/losses.py,sha256=rWKure02dl8hLBzLUs-jhNJV8L3QHWtFbl3HbX
221
223
  torchrl/trainers/helpers/models.py,sha256=VujBq9H92sEzpCtU1iTrJQNlwvyOO-Rho4bzsMonX6s,22465
222
224
  torchrl/trainers/helpers/replay_buffer.py,sha256=RaZqXnHimmadiibvDBcLbtIhpPaVMTPhYMOBvX4v3CA,2060
223
225
  torchrl/trainers/helpers/trainers.py,sha256=hB1FtHtP-S0PBQ4LF6WPy37caaLpacyaLThj1BNl5Ho,12372
224
- torchrl_nightly-2025.6.19.dist-info/LICENSE,sha256=PGO-oZsq4EzhE1-WQS2xGiEF3UCVb9YawfQ09cIMV_8,1119
225
- torchrl_nightly-2025.6.19.dist-info/METADATA,sha256=Sm2baG1GTnimQ4ePO3Wz30u0p8bCG_ulzhHJ842YprI,40044
226
- torchrl_nightly-2025.6.19.dist-info/WHEEL,sha256=yA7mxgqX2UV73NtJdMh2AAmdb628loM81912H3s5r00,100
227
- torchrl_nightly-2025.6.19.dist-info/top_level.txt,sha256=JeTJ1jV7QJwLcUS1nr21aPn_wb-XlAZ9c-z_EH472JA,20
228
- torchrl_nightly-2025.6.19.dist-info/RECORD,,
226
+ torchrl_nightly-2025.6.21.dist-info/LICENSE,sha256=PGO-oZsq4EzhE1-WQS2xGiEF3UCVb9YawfQ09cIMV_8,1119
227
+ torchrl_nightly-2025.6.21.dist-info/METADATA,sha256=Tdeym0nBXEDhFNCxIu74iZKjGWQpYyPCM_IVW801C_I,40044
228
+ torchrl_nightly-2025.6.21.dist-info/WHEEL,sha256=yA7mxgqX2UV73NtJdMh2AAmdb628loM81912H3s5r00,100
229
+ torchrl_nightly-2025.6.21.dist-info/top_level.txt,sha256=JeTJ1jV7QJwLcUS1nr21aPn_wb-XlAZ9c-z_EH472JA,20
230
+ torchrl_nightly-2025.6.21.dist-info/RECORD,,