torchrl-nightly 2025.6.19__cp313-cp313-manylinux1_x86_64.whl → 2025.6.21__cp313-cp313-manylinux1_x86_64.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.cpython-313-x86_64-linux-gnu.so +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=7l8TvVqxKezgzKCLuRv20mvGLloprFVZYm8
3
3
  build_tools/setup_helpers/extension.py,sha256=4-PDLr-pw40bJnd9SfxnTaSjUyuXU_Tg8yOg69Kl0o4,5914
4
4
  torchrl/__init__.py,sha256=mhDBx2UIuBKc0gmi8dVNHokQ6tCbIovruZmyAxcSsy8,2938
5
5
  torchrl/_extension.py,sha256=z7wQ8i1iYWYcnygq_j0nq9sT-koY13tfHhTLNbMk17Q,2353
6
- torchrl/_torchrl.cpython-313-x86_64-linux-gnu.so,sha256=ISfKyibv6LJRpEngEPRIrLbm-MqqoNoRYXtV5m2ENgo,21451184
6
+ torchrl/_torchrl.cpython-313-x86_64-linux-gnu.so,sha256=K2mDnBxDxSj0qflvFxCBKYjue5HjA5oOtzfr9s26sVk,21451208
7
7
  torchrl/_utils.py,sha256=Cw5EG6x5oSZF1iE3YCs1a32VUKp0rTXIs2u67q9zKUI,41078
8
- torchrl/version.py,sha256=ze1tCJcNQxbVdrGYS5E3YBhi11ufrV8zOXkWCgs5tjo,83
8
+ torchrl/version.py,sha256=9TpIavFD2hzZlpmXpm_tjHh5avX5AXfLXuNk_r1S5wc,83
9
9
  torchrl/collectors/__init__.py,sha256=hJ3JD6shRku0BL6SzJQq44FZ5Q1RGR8LealFyU3FRn4,799
10
- torchrl/collectors/collectors.py,sha256=z4DVX32e5-EjBjOSG98rn382g0jL0al8ApLqKhotFyg,176259
10
+ torchrl/collectors/collectors.py,sha256=CdTerIwhCTr6n5OoJLNad0bNQ5OLliPZFWkU18QBKSA,177625
11
11
  torchrl/collectors/utils.py,sha256=MlXrkYuDmV0Em-tVNQiLL32FWgPNDgceYYG_GgpiviA,11320
12
12
  torchrl/collectors/weight_update.py,sha256=nSIfs8ALsfggLoC2ylg1oOAqdGku1tt4e-50JCZJBww,21073
13
13
  torchrl/collectors/distributed/__init__.py,sha256=_24P0ALFunLhL-ls7EsssGUhJkZ_m3nw7krfMTwPqS0,705
@@ -18,12 +18,12 @@ torchrl/collectors/distributed/rpc.py,sha256=0xQDqKlvLmCb_2wL9oZojt4rONaSq09abPL
18
18
  torchrl/collectors/distributed/sync.py,sha256=oZW3nUYrUK52N6pMYX9M0WWhMeTzLl25maxM7X2G8Ec,27272
19
19
  torchrl/collectors/distributed/utils.py,sha256=MuxSeb4TkiyWJYyMyXWLgyCDgtgbGU6g8nNVf59xqCE,6464
20
20
  torchrl/collectors/llm/__init__.py,sha256=rx9DktowQ-gvFleb07US9d9WFc4aNG6zKpiOPSW4A7U,355
21
- torchrl/collectors/llm/base.py,sha256=wyZmNIZ_92lUkfZKgbCh8OXDUoHNhVn_7s4qizmrH58,20388
22
- torchrl/collectors/llm/ray_collector.py,sha256=cc1oZ1zh322lJL21bgJd4b6w9-QUQiCOx2i63zzgMLo,10948
21
+ torchrl/collectors/llm/base.py,sha256=G6n2_U7CIr0BBUMbrOSv-AIRSxFFMqft_Ia3Ir3Ggks,20671
22
+ torchrl/collectors/llm/ray_collector.py,sha256=1o9rbQtoJ48Ovo_YP76KQ-dLlKJt-bGdH2VMaK_-olg,11101
23
23
  torchrl/collectors/llm/utils.py,sha256=-KRSlOmjj34M0c3msP7yS_0DlLmqCijEbf_bADLjzuM,1148
24
24
  torchrl/collectors/llm/weight_update/__init__.py,sha256=bKjvD7yZG5VnHgvYc4EmKI1seK4FyMBKTqeLzkqR_3s,272
25
25
  torchrl/collectors/llm/weight_update/vllm.py,sha256=81ShmKzNjVIg7hxlPvLHhF-YqeXv98cIk0l6ByD-MDU,11276
26
- torchrl/data/__init__.py,sha256=RuBnwrzJqJZxU1drtdzUHdWTrZpL6z4SPLYBYM2AMqc,4769
26
+ torchrl/data/__init__.py,sha256=oowsio6ZUOZnJV8JV43xgs17B37XO1yKAYIQPdk8yt0,4819
27
27
  torchrl/data/rlhf.py,sha256=JUmdYBWgkN229DwpXuDrhy9ddjduNvU2kyHzHR6MoA0,963
28
28
  torchrl/data/tensor_specs.py,sha256=rfuYM9WLUnF4vHwM4opvypShZ3RN7954WhiPMyG3CSU,247841
29
29
  torchrl/data/utils.py,sha256=attuNwzfgjszyp0lJSrV06f2peX3r0qTjRZWEwfl6Yg,12108
@@ -33,18 +33,19 @@ torchrl/data/datasets/common.py,sha256=oK43nmVYoMxlfVqnjCPKLL9dBuYbrHgIK5AQtKgtv
33
33
  torchrl/data/datasets/d4rl.py,sha256=3TWzV-Q3hHk83hky7ab1nvsNEJx5qeI1I4o2331kXwM,19795
34
34
  torchrl/data/datasets/d4rl_infos.py,sha256=pxHgQ2P5uHiVt6sY4NCQfqOU6dL_QwdFYtdpTnEju0o,22570
35
35
  torchrl/data/datasets/gen_dgrl.py,sha256=62ryTA9QRIVYiA9RisEithHI_Q4lKvf7qD3xP-3VEN4,14293
36
- torchrl/data/datasets/minari_data.py,sha256=9bXXlT_3nTSpOC5tW1EgpNiHhQH8752vKrkKDheHE_0,20718
36
+ torchrl/data/datasets/minari_data.py,sha256=q2VeBZzLFpKTjreSmiSYCQgfbkcL4UoCpYFXBW8Fz8o,20718
37
37
  torchrl/data/datasets/openml.py,sha256=q_xO35-wTV2kLCwd6pIo9yHAPSKSjfJToq9Ke8k5VWc,7009
38
38
  torchrl/data/datasets/openx.py,sha256=QXjJPZHoRhefVux00iAL-g4spynrWjmI_M2IuaQ8TA0,33264
39
39
  torchrl/data/datasets/roboset.py,sha256=rLPdyEQI9yEibXU6SZFA0YD79EGFKY8o5oyUlvcn4aM,16648
40
40
  torchrl/data/datasets/utils.py,sha256=nAFDTlBIPyEoPoJC-Hc_fcOhzE7UZQE4BwKxq15Vhvk,339
41
41
  torchrl/data/datasets/vd4rl.py,sha256=z90MqrxKzod8TPGK0uzkC6vw5wQIE4cgrDAC4e72jyk,18262
42
- torchrl/data/llm/__init__.py,sha256=FWApDyEPlyE7jA7CRMmGpxnLYQ4ZKKAdCbbpmOMf-OU,908
43
- torchrl/data/llm/chat.py,sha256=Qe6nVBG999uJNAtHtPOUMbXBumH9UD4WufH7n36klEw,30818
42
+ torchrl/data/llm/__init__.py,sha256=By2FWnjqADPmHnNXh6DVLQ9CYPj51gn3HxPW_DYPMyc,971
43
+ torchrl/data/llm/chat.py,sha256=K5Cuw4GHSJWGg5vXwGyV9oqS7X0ddcx1FA1sUNEvjKY,33174
44
44
  torchrl/data/llm/common.py,sha256=CYBaAop8QETotOCBGTw_pfKjxFYlsoSGElki6wBx5jo,2135
45
45
  torchrl/data/llm/dataset.py,sha256=t-41hAzQcjrdoKwpHIMbcrT7pRcQ7DHl2a1-lr6E7W4,20703
46
46
  torchrl/data/llm/prompt.py,sha256=bg5LzJfwOq5Ns72KQMciIprMWAmDDinzdopwdopU04c,8380
47
47
  torchrl/data/llm/reward.py,sha256=FbPchNXG3smJV9NCbB5Yk4grsCa2Se4KZ_tojVLKWQM,8404
48
+ torchrl/data/llm/topk.py,sha256=SZq89yeFr8rNbpVR-S5vC7AVoeb6JKYZPeSS-n4FwKE,8353
48
49
  torchrl/data/llm/utils.py,sha256=axe3wSovfWBm5YmR_uJYpfAmYtd__2i9SCKgUSezkBk,23600
49
50
  torchrl/data/map/__init__.py,sha256=1IB8lWApscQOOscsCEhQrUDy_AE1wWV51Tcl1Segsqk,555
50
51
  torchrl/data/map/hash.py,sha256=29cKgYjd5vVeR2bu2kI5BwtOq9FeZD41RA7Q3UxP9vo,7252
@@ -56,11 +57,11 @@ torchrl/data/postprocs/__init__.py,sha256=Z9JpRKMGsuFGpB3ro4R9Y_hYTBqkkzbkWZR79T
56
57
  torchrl/data/postprocs/postprocs.py,sha256=h8LO8zBosRm7iLmUOxdtPxZ84yavkv9usYtLSBq9tC4,15118
57
58
  torchrl/data/replay_buffers/__init__.py,sha256=v_oKflSohims6uw40XhLkjDX7vZM9UwXrWAeZfftogw,2360
58
59
  torchrl/data/replay_buffers/checkpointers.py,sha256=VF18DlRiy361gecbT2HL5VLTQU4Faxq7mULsownjYiQ,14790
59
- torchrl/data/replay_buffers/ray_buffer.py,sha256=joYh_ypj4Zk2CNUEdfgNiAybvA8vNJTmrAlwC1bhejg,9043
60
- torchrl/data/replay_buffers/replay_buffers.py,sha256=c0yoPBzQjfWfTLOXbPj7VqA-ZnTP_7oS0OVpwo5gaPk,88639
61
- torchrl/data/replay_buffers/samplers.py,sha256=HZguztdX2tvDwIPKT0STAKuncJi8l005FCuuNKnAVoE,105427
60
+ torchrl/data/replay_buffers/ray_buffer.py,sha256=at8rYXxtlctoPCnL5oJRNoEkjEASHoXjPIt6UH16OCA,9854
61
+ torchrl/data/replay_buffers/replay_buffers.py,sha256=lKTcEQOooT_MY4cuVuAdaYPKN9Ob9v3o46FGdnCyOS8,90459
62
+ torchrl/data/replay_buffers/samplers.py,sha256=Kp48OPzvEWeTbPS8LNMRiGaYwUdrMgVVc3OaRIkNIR4,110296
62
63
  torchrl/data/replay_buffers/scheduler.py,sha256=SRZf_FJLUEIBz684W9RlLt3In158s9N5h4xb_MWnBgY,10152
63
- torchrl/data/replay_buffers/storages.py,sha256=WnNopbDT3DbjiN7QRdb-Iet-sLBmt7hSfEnKDx1-VEI,59579
64
+ torchrl/data/replay_buffers/storages.py,sha256=9h2iyLv9jnKG7kB1925SRlcxly-IABqGjPhoMGov-6Y,60704
64
65
  torchrl/data/replay_buffers/utils.py,sha256=tU98Nc_j9bMrWBs96gFUTDXLmWEZCvHRYjSXjPMc_lY,38603
65
66
  torchrl/data/replay_buffers/writers.py,sha256=p9b8k89u-JrqoObT4aCLa0qCkKWdM__l7lGUQDKSdsU,27727
66
67
  torchrl/envs/__init__.py,sha256=c-_VtMuAcRdg0hBmltn6AbTU7B1X-ARBEfqOQoPFEZk,5817
@@ -96,8 +97,8 @@ torchrl/envs/libs/smacv2.py,sha256=i0TRHuZ9S9v0NfufPgQAcTlvAjf6JKv8hHvOzjSgsaw,2
96
97
  torchrl/envs/libs/unity_mlagents.py,sha256=Z3qSU0H3o2NXbS2lNvQ7OmYxkr3AWAMyRHfxeCtNZrk,49667
97
98
  torchrl/envs/libs/utils.py,sha256=RgiR16KJWFEtQim44-AIcHByGTq_NrtpjWoYIC13aYA,5207
98
99
  torchrl/envs/libs/vmas.py,sha256=a71_jU4r627hFXcMsT5wNSb4TMpyd3punLdOF3Cc8O0,36297
99
- torchrl/envs/llm/__init__.py,sha256=DiYt8YjoxmwoM62XPtNUPMYaqZyf1UXY6dAD_vcBIfE,1221
100
- torchrl/envs/llm/chat.py,sha256=DT_kcsfpM0W3bayRVk3rdtNKyv3pjoOsicw56LG6fp8,17619
100
+ torchrl/envs/llm/__init__.py,sha256=o8uAVGHYngy_k6xM5qIkqgHaz__S1HyG7QjLd78gtaA,1265
101
+ torchrl/envs/llm/chat.py,sha256=mVLjmBTwd6IWdlKJMRcynDJNVVbiHjCop5EVUXpaaAA,17794
101
102
  torchrl/envs/llm/envs.py,sha256=Er-ahjgvtYG4LB7_EWOMbdobiUV5DOHPBQYkVTu80r4,34677
102
103
  torchrl/envs/llm/datasets/__init__.py,sha256=FFethtv8unJWzphGLPQVC5QD9NMdaygEjx25O1DHHZk,473
103
104
  torchrl/envs/llm/datasets/gsm8k.py,sha256=wTntpV-bi0gbyvJ-JnuHQmPXjXgV4hEssGFed8GRGGc,15299
@@ -105,18 +106,18 @@ torchrl/envs/llm/datasets/ifeval.py,sha256=fVbMSVjpnlZR36B0yDUgDcM1Ye-EP6ui7g9nP
105
106
  torchrl/envs/llm/libs/__init__.py,sha256=vhEm5Fhz1sLWt107zfZLy5pzGmfQi0fNBGazTq1m7dU,266
106
107
  torchrl/envs/llm/libs/mlgym.py,sha256=ECnkrNoPV73L1fIO05SlTTXuTSNOM2pdX6aJcEYJVlo,31372
107
108
  torchrl/envs/llm/reward/__init__.py,sha256=a-Xsye29z2LugO1cOCFM2FNsqNwEp-5XwQk4saVQlu8,370
108
- torchrl/envs/llm/reward/gsm8k.py,sha256=6y6I8UdPanS6g7skWFStNm_nXP0nS5ctcAHFWEkFup0,7702
109
+ torchrl/envs/llm/reward/gsm8k.py,sha256=2pUXYkCw6_arM6HCZJcrEYwRZMDntsFAzdpf3QXNthI,7862
109
110
  torchrl/envs/llm/reward/ifeval/__init__.py,sha256=g5NtrwfwqK22hRcoIdz8-KWBh5Ogre9J-Bf3uGWE9Pg,314
110
111
  torchrl/envs/llm/reward/ifeval/_instructions.py,sha256=rAoTdwG42smCLJgwW7kAwJrNonjIS6OwdohDE70oMOA,61696
111
112
  torchrl/envs/llm/reward/ifeval/_instructions_main.py,sha256=CofKXvG0J2H-1ZXP1fL6UZI8ArNCIO2w5R_37drRIW8,4117
112
113
  torchrl/envs/llm/reward/ifeval/_instructions_registry.py,sha256=3_guc8LZ0mWQc-n6E4cQgYMgZRYa6xfgvXgrze9aO_w,3814
113
114
  torchrl/envs/llm/reward/ifeval/_instructions_util.py,sha256=aA3fupO8MvqBCqD7Y_Qk6y32toWF1lZGAflWON1ruXM,26042
114
115
  torchrl/envs/llm/reward/ifeval/_scorer.py,sha256=zJHBgaGlluEv6czsI6ZtLqArV_J_W9zY7UPAJhT5YIo,14563
115
- torchrl/envs/llm/transforms/__init__.py,sha256=fpcS83ud3OC2NWnkFeTdE8r4Mtlbcp_OiITzDM03aes,748
116
+ torchrl/envs/llm/transforms/__init__.py,sha256=roEOZVFOs1PhC1cGF-LIXQt5DlXZx6mgIJ-1k0JDTfI,788
116
117
  torchrl/envs/llm/transforms/browser.py,sha256=zF7jHHHrdpxUCjFFtiYK-vhw-p1YqsqwP8_b4SiK0Rs,10423
117
118
  torchrl/envs/llm/transforms/dataloading.py,sha256=dv4IV3OWEa6-evxBk3WAZjkBi1_yKUs2NQ2gGmL2lKQ,24533
118
119
  torchrl/envs/llm/transforms/format.py,sha256=ESn0S9k5G4FQPBICq9h6ZsLKXZqiU71tYW8UnW4rgLI,2519
119
- torchrl/envs/llm/transforms/kl.py,sha256=lRWW1Gf8bu71jMatAlk91Eeuh50mmPedjKrnXKUm5D0,11721
120
+ torchrl/envs/llm/transforms/kl.py,sha256=N68378chSx54X5a7YLJzIV6d870H5xrBb5-qWqzpX1U,22744
120
121
  torchrl/envs/llm/transforms/policy_version.py,sha256=by2TjsZLwVjQbq7ggBoAco2Iq_2aEYgyxh9asTXL1vk,6893
121
122
  torchrl/envs/llm/transforms/tokenizer.py,sha256=CcuKRu33YnyDgLtQtyxTGDFC6iI3b3fUA6Nb1Lnh7h8,13953
122
123
  torchrl/envs/llm/transforms/tools.py,sha256=I-HR0zjH4tFMp9xPH556H5Q5JqmqXdsAXwElAR93e5U,29498
@@ -130,7 +131,7 @@ torchrl/envs/transforms/llm.py,sha256=rQDzuut807wvFpSPCm5tynt8-cMKTgVKVjSVu9D99P
130
131
  torchrl/envs/transforms/r3m.py,sha256=sdTVLpnxHfzFVo5rO8WnXf2uUg9cr4LBOLBsWaFgGT8,13478
131
132
  torchrl/envs/transforms/rb_transforms.py,sha256=pxtL1VHvzEq6djuWsccLu4P-tnbAKsavemLGyt80I6c,7448
132
133
  torchrl/envs/transforms/rlhf.py,sha256=lOVXYqQaoDfm4_n77Dxw_wjicBpMtDvavKmBIK2N3lU,628
133
- torchrl/envs/transforms/transforms.py,sha256=QC0T86dGyXa_MJcUKNZ_WU0e92BBw4ibkAHAcSvh8LQ,480320
134
+ torchrl/envs/transforms/transforms.py,sha256=59WHIbGryXTSvswHxvQSxHAza1k5-qtxwfWRzd6MQ6M,479710
134
135
  torchrl/envs/transforms/utils.py,sha256=VXGH69Jxdmnw5eP9L3uM8ronQA5aIbT-Ktpjn5Frds0,2058
135
136
  torchrl/envs/transforms/vc1.py,sha256=mho5BvdAK-f9hD9t-iah52wT2B06qPmaJO7chrfIOWY,10534
136
137
  torchrl/envs/transforms/vecnorm.py,sha256=XahMcWvK3zjOB6EACSZtJ6UMP3yQ2zD9xf87UEB37Eg,34047
@@ -147,8 +148,8 @@ torchrl/modules/llm/backends/__init__.py,sha256=WdVy9EdiAfk8i5zFa49TEkRvcUd0L4Un
147
148
  torchrl/modules/llm/backends/vllm.py,sha256=x57Xop1xd5ZShicsh47ZFmz4VpfZ3eCzVx7k0COvpqQ,9387
148
149
  torchrl/modules/llm/policies/__init__.py,sha256=rVQwVhSTS1hLcSynvPXKq9_9gGC6gC1SyOz5DNg1qcc,426
149
150
  torchrl/modules/llm/policies/common.py,sha256=m76rSjgYbf-ZMEUFZNbjBbyXNHbR8BXt1z5o9honJOM,3019
150
- torchrl/modules/llm/policies/transformers_wrapper.py,sha256=yn_qVpFqjr41HrkkxGhLDfIjtS9PCgklnbkAecu4Evc,22615
151
- torchrl/modules/llm/policies/vllm_wrapper.py,sha256=g3eaQSNti6NQBpKcokeLL9b0K3Kt38ltaPv8qlIIqDo,29782
151
+ torchrl/modules/llm/policies/transformers_wrapper.py,sha256=M0Drk7MFY596Ek8_duNTXFpc4c2Ar94Jy3viXnhRS2M,25370
152
+ torchrl/modules/llm/policies/vllm_wrapper.py,sha256=1vwfoIYxOL2IwBMVZUFrwOexIwS7x1xbhBVdru6gYxY,31487
152
153
  torchrl/modules/models/__init__.py,sha256=DrOG-7hynjjUh_tc2EqysiUiNMRiDR0WLtZql9TPNcI,1743
153
154
  torchrl/modules/models/batchrenorm.py,sha256=TojpTUluIcFdTSemIVRLGtB2O5q54mRHy3vJP6DuI5I,4750
154
155
  torchrl/modules/models/decision_transformer.py,sha256=Lttf_wZMNqXbB_vpxMYgEp18gEzOvm3NvMnxQkHkH4M,6604
@@ -187,15 +188,16 @@ torchrl/objectives/dreamer.py,sha256=vIJQN91oPXYnPubDFQpaF5d3fR_WwIYuIVYtoCvw0TY
187
188
  torchrl/objectives/functional.py,sha256=ZaglBjEGuOTNGeFA-Ox-ugZVcNegQMUj--KWHDRBmaU,2106
188
189
  torchrl/objectives/gail.py,sha256=0m34XmcN-EDk5OfNIo5bKYbKKZfATsYRv4zQe3v2UwA,9576
189
190
  torchrl/objectives/iql.py,sha256=1jvlSznWke6NZSwfuYyHVnVBE7Cz3q169GnCRC7iel4,42991
190
- torchrl/objectives/ppo.py,sha256=vWgF0b_XjPxbOwXZUGEukFsq0k_zZ1DR3J270EAXn-0,73795
191
+ torchrl/objectives/ppo.py,sha256=qoG7YiHHz6M5jn3XgtE32AmMERianoZqs-lSHQA35Rg,75284
191
192
  torchrl/objectives/redq.py,sha256=4usM-nG2UWujeL-VEqzf7-uOwRFx6itkKCeitKuJhtw,28507
192
193
  torchrl/objectives/reinforce.py,sha256=ySXLp5C-OOUYayqjrf4taQmL8LgRvMgPCgHDsle8JDc,22339
193
194
  torchrl/objectives/sac.py,sha256=Oq9Iq90s9KFbnM4KSRUd2onU1JfW6aW80LWGdtO0CY8,63993
194
195
  torchrl/objectives/td3.py,sha256=RnlkGzBBTY0KrfRKytsFbNyoVUy2HLfwSL4_9YQRep8,23190
195
196
  torchrl/objectives/td3_bc.py,sha256=jHGwCzPuCbN37zAxsiDQIe92yR1UE7rjcnJoy8b_NjE,25950
196
197
  torchrl/objectives/utils.py,sha256=nhB7a2gLoZMLgYSWTpSgQqZWEGRBkvVoa8yszTlecm4,24001
197
- torchrl/objectives/llm/__init__.py,sha256=LnYwAuaG-ylQQcu2BRQWavaDhjMPikXNT6YaH_3QoEU,328
198
+ torchrl/objectives/llm/__init__.py,sha256=SXYwry5YoDp5m0QRFmOYzz60siJQmofcTvCOmC1DlXw,396
198
199
  torchrl/objectives/llm/grpo.py,sha256=rsPVvfE_2Bbl8K1aq_LIry1ViDnibfGYWexfSIbJx80,16788
200
+ torchrl/objectives/llm/sft.py,sha256=zAdVT1CmXJJPjEwPt4SPJNzFUC2m-flcfOsejIuAFkg,20107
199
201
  torchrl/objectives/multiagent/__init__.py,sha256=CHxWmq5_3kveLcAdyB7cgSVYVIald7EZo81RRgozxo0,237
200
202
  torchrl/objectives/multiagent/qmixer.py,sha256=JyDcZeV2zv2MqKsyJ-ql9ISYHJ58e3pzb5-0BThswhI,16973
201
203
  torchrl/objectives/value/__init__.py,sha256=AdluF370wYzOAcP_yglUAFnNByKVZzivBYJafkDQbJA,561
@@ -221,8 +223,8 @@ torchrl/trainers/helpers/losses.py,sha256=qH-2YJwMtDAYAPXTTYy3cOPiq4ILC6xTjfnGUU
221
223
  torchrl/trainers/helpers/models.py,sha256=ihTERG2c96E8cS3Tnul6a_ys6iDEEJmHh05p9blQTW8,21807
222
224
  torchrl/trainers/helpers/replay_buffer.py,sha256=ZUZHOa0TILyeWJ3iahzTJ6UvMl_0FdxuZfJEja94Bn8,2001
223
225
  torchrl/trainers/helpers/trainers.py,sha256=j6B5XA7_FFHMQeOIQwjNcO0CGE_4mZKUC9_jH_iqqh4,12071
224
- torchrl_nightly-2025.6.19.dist-info/LICENSE,sha256=xdjS4_xk-IwnLuIFCvTYTl9Y8aXRejqpmke3dGam_nI,1098
225
- torchrl_nightly-2025.6.19.dist-info/METADATA,sha256=chdJhBnG0Non4uOX8TKbXKqBm_i2YFKNl4SUWMek5DI,39023
226
- torchrl_nightly-2025.6.19.dist-info/WHEEL,sha256=HRqO1yy0EkQFVSOPjhgaTzf773tbWecKJXRlZH64XT8,104
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=xdjS4_xk-IwnLuIFCvTYTl9Y8aXRejqpmke3dGam_nI,1098
227
+ torchrl_nightly-2025.6.21.dist-info/METADATA,sha256=FbFAW_HINLwiA_5Vi6WG31aQU6K9088TRaz-QcHO5nA,39023
228
+ torchrl_nightly-2025.6.21.dist-info/WHEEL,sha256=HRqO1yy0EkQFVSOPjhgaTzf773tbWecKJXRlZH64XT8,104
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,,