From 1f1be7e6fcade8c0418ccd59452b00e5f41aabdc Mon Sep 17 00:00:00 2001 From: Ethan Almloff <76850177+NoodlesOfWrath@users.noreply.github.com> Date: Thu, 23 Oct 2025 09:42:48 -0500 Subject: [PATCH] update modurl + test cartpole determinism --- Cargo.lock | 163 ++++++++++++++++---------------- Cargo.toml | 3 +- src/classic_control/cartpole.rs | 45 +++++++++ 3 files changed, 128 insertions(+), 83 deletions(-) diff --git a/Cargo.lock b/Cargo.lock index 46b9a57..5b69c9e 100644 --- a/Cargo.lock +++ b/Cargo.lock @@ -36,9 +36,9 @@ checksum = "bef38d45163c2f1dde094a7dfd33ccf595c92905c8f8f4fdc18d06fb1037718a" [[package]] name = "bitflags" -version = "2.9.4" +version = "2.10.0" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "2261d10cca569e4643e526d8dc2e62e433cc8aba21ab764233731f8d369bf394" +checksum = "812e12b5285cc515a9c72a5c1d3b6d46a19dac5acfef5265968c166106e31dd3" [[package]] name = "block" @@ -57,9 +57,9 @@ dependencies = [ [[package]] name = "bon" -version = "3.7.2" +version = "3.8.1" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "c2529c31017402be841eb45892278a6c21a000c0a17643af326c73a73f83f0fb" +checksum = "ebeb9aaf9329dff6ceb65c689ca3db33dbf15f324909c60e4e5eef5701ce31b1" dependencies = [ "bon-macros", "rustversion", @@ -67,9 +67,9 @@ dependencies = [ [[package]] name = "bon-macros" -version = "3.7.2" +version = "3.8.1" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "d82020dadcb845a345591863adb65d74fa8dc5c18a0b6d408470e13b7adc7005" +checksum = "77e9d642a7e3a318e37c2c9427b5a6a48aa1ad55dcd986f3034ab2239045a645" dependencies = [ "darling", "ident_case", @@ -86,7 +86,7 @@ version = "0.0.4" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "5150004def1b5eb8db8c80fac41437dabda563ccc49f8a71dac4ffd132615ba5" dependencies = [ - "bitflags 2.9.4", + "bitflags 2.10.0", ] [[package]] @@ -97,18 +97,18 @@ checksum = "46c5e41b57b8bba42a04676d81cb89e9ee8e859a1a66f80a5a72e1cb76b34d43" [[package]] name = "bytemuck" -version = "1.23.2" +version = "1.24.0" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "3995eaeebcdf32f91f980d360f78732ddc061097ab4e39991ae7a6ace9194677" +checksum = "1fbdf580320f38b612e485521afda1ee26d10cc9884efaaa750d383e13e3c5f4" dependencies = [ "bytemuck_derive", ] [[package]] name = "bytemuck_derive" -version = "1.10.1" +version = "1.10.2" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "4f154e572231cb6ba2bd1176980827e3d5dc04cc183a75dea38109fbdd672d29" +checksum = "f9abbd1bc6865053c427f7198e6af43bfdedc55ab791faed4fbd361d789575ff" dependencies = [ "proc-macro2", "quote", @@ -189,9 +189,9 @@ dependencies = [ [[package]] name = "cc" -version = "1.2.39" +version = "1.2.41" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "e1354349954c6fc9cb0deab020f27f783cf0b604e8bb754dc4658ecf0d29c35f" +checksum = "ac9fe6cdbb24b6ade63616c0a0688e45bb56732262c158df3c0c4bea4ca47cb7" dependencies = [ "find-msvc-tools", "shlex", @@ -199,9 +199,9 @@ dependencies = [ [[package]] name = "cfg-if" -version = "1.0.3" +version = "1.0.4" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "2fd1289c04a9ea8cb22300a459a72a385d7c73d3259e2ed7dcb2af674838cfa9" +checksum = "9330f8b2ff13f34540b44e946ef35111825727b38d33286ef986142615121801" [[package]] name = "console_error_panic_hook" @@ -343,7 +343,7 @@ version = "0.3.0" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "89a09f22a6c6069a18470eb92d2298acf25463f14256d24778e1230d789a2aec" dependencies = [ - "bitflags 2.9.4", + "bitflags 2.10.0", "objc2", ] @@ -385,13 +385,20 @@ dependencies = [ [[package]] name = "dyn-stack" -version = "0.13.0" +version = "0.13.2" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "490bd48eb68fffcfed519b4edbfd82c69cbe741d175b84f0e0cbe8c57cbe0bdd" +checksum = "1c4713e43e2886ba72b8271aa66c93d722116acf7a75555cce11dcde84388fe8" dependencies = [ "bytemuck", + "dyn-stack-macros", ] +[[package]] +name = "dyn-stack-macros" +version = "0.1.3" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "e1d926b4d407d372f141f93bb444696142c29d32962ccbd3531117cf3aa0bfa9" + [[package]] name = "either" version = "1.15.0" @@ -434,9 +441,9 @@ checksum = "37909eebbb50d72f9059c3b6d82c0463f2ff062c9e95845c43a6c9c0355411be" [[package]] name = "find-msvc-tools" -version = "0.1.2" +version = "0.1.4" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "1ced73b1dacfc750a6db6c0a0c3a3853c8b41997e2e2c563dc90804ae6867959" +checksum = "52051878f80a721bb68ebfbc930e07b65ba72f2da88968ea5c06fd6ca3d3a127" [[package]] name = "float8" @@ -608,7 +615,7 @@ version = "0.18.2" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "ab96b703d31950f1aeddded248bc95543c9efc7ac9c4a21fda8703a83ee35451" dependencies = [ - "dyn-stack 0.13.0", + "dyn-stack 0.13.2", "gemm-c32 0.18.2", "gemm-c64 0.18.2", "gemm-common 0.18.2", @@ -643,7 +650,7 @@ version = "0.18.2" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "f6db9fd9f40421d00eea9dd0770045a5603b8d684654816637732463f4073847" dependencies = [ - "dyn-stack 0.13.0", + "dyn-stack 0.13.2", "gemm-common 0.18.2", "num-complex", "num-traits", @@ -673,7 +680,7 @@ version = "0.18.2" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "dfcad8a3d35a43758330b635d02edad980c1e143dc2f21e6fd25f9e4eada8edf" dependencies = [ - "dyn-stack 0.13.0", + "dyn-stack 0.13.2", "gemm-common 0.18.2", "num-complex", "num-traits", @@ -709,7 +716,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "a352d4a69cbe938b9e2a9cb7a3a63b7e72f9349174a2752a558a8a563510d0f3" dependencies = [ "bytemuck", - "dyn-stack 0.13.0", + "dyn-stack 0.13.2", "half", "libm", "num-complex", @@ -747,7 +754,7 @@ version = "0.18.2" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "cff95ae3259432f3c3410eaa919033cd03791d81cebd18018393dc147952e109" dependencies = [ - "dyn-stack 0.13.0", + "dyn-stack 0.13.2", "gemm-common 0.18.2", "gemm-f32 0.18.2", "half", @@ -780,7 +787,7 @@ version = "0.18.2" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "bc8d3d4385393304f407392f754cd2dc4b315d05063f62cf09f47b58de276864" dependencies = [ - "dyn-stack 0.13.0", + "dyn-stack 0.13.2", "gemm-common 0.18.2", "num-complex", "num-traits", @@ -810,7 +817,7 @@ version = "0.18.2" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "35b2a4f76ce4b8b16eadc11ccf2e083252d8237c1b589558a49b0183545015bd" dependencies = [ - "dyn-stack 0.13.0", + "dyn-stack 0.13.2", "gemm-common 0.18.2", "num-complex", "num-traits", @@ -821,14 +828,14 @@ dependencies = [ [[package]] name = "getrandom" -version = "0.3.3" +version = "0.3.4" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "26145e563e54f2cadc477553f1ec5ee650b00862f0a58bcd12cbdc5f0ea2d2f4" +checksum = "899def5c37c4fd7b2664648c28120ecec138e4d395b459e5ca34f9cce2dd77fd" dependencies = [ "cfg-if", "libc", "r-efi", - "wasi", + "wasip2", ] [[package]] @@ -839,9 +846,9 @@ checksum = "0cc23270f6e1808e30a928bdc84dea0b9b4136a8bc82338574f23baf47bbd280" [[package]] name = "half" -version = "2.6.0" +version = "2.7.1" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "459196ed295495a68f7d7fe1d84f6c4b7ff0e21fe3017b2f283c6fac3ad803c9" +checksum = "6ea2d84b969582b4b1864a92dc5d27cd2b77b622a8d79306834f1be5ba20d84b" dependencies = [ "bytemuck", "cfg-if", @@ -849,6 +856,7 @@ dependencies = [ "num-traits", "rand", "rand_distr", + "zerocopy", ] [[package]] @@ -877,9 +885,9 @@ checksum = "b9e0384b61958566e926dc50660321d12159025e767c18e043daf26b70104c39" [[package]] name = "indexmap" -version = "2.11.4" +version = "2.12.0" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "4b0f83760fb341a774ed326568e19f5a863af4a952def8c39f9ab92fd95b88e5" +checksum = "6717a8d2a5a929a1a2eb43a12812498ed141a0bcfb7e8f7844fbdbe4303bba9f" dependencies = [ "equivalent", "hashbrown", @@ -921,9 +929,9 @@ checksum = "bbd2bcb4c963f2ddae06a2efc7e9f3591312473c50c6685e1f298068316e66fe" [[package]] name = "libc" -version = "0.2.176" +version = "0.2.177" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "58f929b4d672ea937a23a1ab494143d968337a5f47e56d0815df1e0890ddf174" +checksum = "2874a2af47a2325c2001a6e6fad9b16a53b802102b528163885171cf92b15976" [[package]] name = "libloading" @@ -947,7 +955,7 @@ version = "0.1.10" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "416f7e718bdb06000964960ffa43b4335ad4012ae8b99060261aa4a8088d5ccb" dependencies = [ - "bitflags 2.9.4", + "bitflags 2.10.0", "libc", "redox_syscall", ] @@ -981,9 +989,9 @@ checksum = "f52b00d39961fc5b2736ea853c9cc86238e165017a493d1d5c8eac6bdc4cc273" [[package]] name = "memmap2" -version = "0.9.8" +version = "0.9.9" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "843a98750cd611cc2965a8213b53b43e715f13c37a9e096c6408e69990961db7" +checksum = "744133e4a0e0a658e1374cf3bf8e415c4052a15a111acd372764c55b4177d490" dependencies = [ "libc", "stable_deref_trait", @@ -1004,7 +1012,7 @@ version = "0.29.0" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "7ecfd3296f8c56b7c1f6fbac3c71cefa9d78ce009850c45000015f206dc7fa21" dependencies = [ - "bitflags 2.9.4", + "bitflags 2.10.0", "block", "core-graphics-types", "foreign-types", @@ -1045,7 +1053,7 @@ dependencies = [ [[package]] name = "modurl" version = "0.1.0" -source = "git+https://github.com/ModuRL/ModuRL?branch=implement-determinism#f23058ff76908602e78ec1d84239960df7d81f14" +source = "git+https://github.com/ModuRL/ModuRL#4ddf128916401d05b7904f8164f8e34a14362cf0" dependencies = [ "bon", "candle-core", @@ -1167,9 +1175,9 @@ dependencies = [ [[package]] name = "num_enum" -version = "0.7.4" +version = "0.7.5" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "a973b4e44ce6cad84ce69d797acf9a044532e4184c4f267913d1b546a0727b7a" +checksum = "b1207a7e20ad57b847bbddc6776b968420d38292bbfe2089accff5e19e82454c" dependencies = [ "num_enum_derive", "rustversion", @@ -1177,9 +1185,9 @@ dependencies = [ [[package]] name = "num_enum_derive" -version = "0.7.4" +version = "0.7.5" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "77e878c846a8abae00dd069496dbe8751b16ac1c3d6bd2a7283a938e8228f90d" +checksum = "ff32365de1b6743cb203b710788263c44a03de03802daf96092f2da4fe6ba4d7" dependencies = [ "proc-macro-crate", "proc-macro2", @@ -1211,7 +1219,7 @@ version = "0.3.2" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "2a180dd8642fa45cdb7dd721cd4c11b1cadd4929ce112ebd8b9f5803cc79d536" dependencies = [ - "bitflags 2.9.4", + "bitflags 2.10.0", "dispatch2", "objc2", ] @@ -1228,7 +1236,7 @@ version = "0.3.2" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "e3e0adef53c21f888deb4fa59fc59f7eb17404926ee8a6f59f5df0fd7f9f3272" dependencies = [ - "bitflags 2.9.4", + "bitflags 2.10.0", "block2", "libc", "objc2", @@ -1241,7 +1249,7 @@ version = "0.3.2" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "a0125f776a10d00af4152d74616409f0d4a2053a6f57fa5b7d6aa2854ac04794" dependencies = [ - "bitflags 2.9.4", + "bitflags 2.10.0", "block2", "dispatch2", "objc2", @@ -1321,9 +1329,9 @@ dependencies = [ [[package]] name = "proc-macro2" -version = "1.0.101" +version = "1.0.102" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "89ae43fd86e4158d6db51ad8e2b80f313af9cc74f5c0e03ccb87de09998732de" +checksum = "8e0f6df8eaa422d97d72edcd152e1451618fed47fabbdbd5a8864167b1d4aff7" dependencies = [ "unicode-ident", ] @@ -1423,7 +1431,7 @@ version = "11.6.0" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "498cd0dc59d73224351ee52a95fee0f1a617a2eae0e7d9d720cc622c73a54186" dependencies = [ - "bitflags 2.9.4", + "bitflags 2.10.0", ] [[package]] @@ -1460,11 +1468,11 @@ checksum = "03251193000f4bd3b042892be858ee50e8b3719f2b08e5833ac4353724632430" [[package]] name = "redox_syscall" -version = "0.5.17" +version = "0.5.18" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "5407465600fb0548f1442edf71dd20683c6ed326200ace4b1ef0763521bb3b77" +checksum = "ed2bf2547551a7053d6fdfafda3f938979645c44812fbfcda098faae3f1a362d" dependencies = [ - "bitflags 2.9.4", + "bitflags 2.10.0", ] [[package]] @@ -1473,7 +1481,7 @@ version = "1.1.2" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "cd15f8a2c5551a84d56efdc1cd049089e409ac19a3072d5037a17fd70719ff3e" dependencies = [ - "bitflags 2.9.4", + "bitflags 2.10.0", "errno", "libc", "linux-raw-sys", @@ -1609,9 +1617,9 @@ checksum = "67b1b7a3b5fe4f1376887184045fcf45c69e92af734b7aaddc05fb777b6fbd03" [[package]] name = "stable_deref_trait" -version = "1.2.0" +version = "1.2.1" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "a8f112729512f8e442d81f95a8a7ddf2b7c6b8a1a6f509a95864142b30cab2d3" +checksum = "6ce2be8dc25455e1f91df71bfa12ad37d7af1092ae736f3a6cd0e37bc7810596" [[package]] name = "strsim" @@ -1621,9 +1629,9 @@ checksum = "7da8b5736845d9f2fcb837ea5d9e2628564b3b043a70948a3f0b778838c5fb4f" [[package]] name = "syn" -version = "2.0.106" +version = "2.0.108" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "ede7c438028d4436d71104916910f5bb611972c5cfd7f89b8300a8186e6fada6" +checksum = "da58917d35242480a05c2897064da0a80589a2a0476c9a3f2fdc83b53502e917" dependencies = [ "proc-macro2", "quote", @@ -1647,7 +1655,7 @@ version = "0.5.5" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "ec7dddc5f0fee506baf8b9fdb989e242f17e4b11c61dfbb0635b705217199eea" dependencies = [ - "bitflags 2.9.4", + "bitflags 2.10.0", "byteorder", "enum-as-inner", "libc", @@ -1661,7 +1669,7 @@ version = "0.6.0" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "01198a2debb237c62b6826ec7081082d951f46dbb64b0e8c7649a452230d1dfc" dependencies = [ - "bitflags 2.9.4", + "bitflags 2.10.0", "byteorder", "enum-as-inner", "libc", @@ -1704,18 +1712,18 @@ dependencies = [ [[package]] name = "toml_datetime" -version = "0.7.2" +version = "0.7.3" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "32f1085dec27c2b6632b04c80b3bb1b4300d6495d1e129693bdda7d91e72eec1" +checksum = "f2cdb639ebbc97961c51720f858597f7f24c4fc295327923af55b74c3c724533" dependencies = [ "serde_core", ] [[package]] name = "toml_edit" -version = "0.23.6" +version = "0.23.7" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "f3effe7c0e86fdff4f69cdd2ccc1b96f933e24811c5441d44904e8683e27184b" +checksum = "6485ef6d0d9b5d0ec17244ff7eb05310113c3f316f2d14200d4de56b3cb98f8d" dependencies = [ "indexmap", "toml_datetime", @@ -1725,9 +1733,9 @@ dependencies = [ [[package]] name = "toml_parser" -version = "1.0.3" +version = "1.0.4" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "4cf893c33be71572e0e9aa6dd15e6677937abd686b066eac3f8cd3531688a627" +checksum = "c0cbe268d35bdb4bb5a56a2de88d0ad0eb70af5384a99d648cd4b3d04039800e" dependencies = [ "winnow", ] @@ -1813,9 +1821,9 @@ dependencies = [ [[package]] name = "unicode-ident" -version = "1.0.19" +version = "1.0.20" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "f63a545481291138910575129486daeaf8ac54aee4387fe7906919f7830c7d9d" +checksum = "462eeb75aeb73aea900253ce739c8e18a67423fadf006037cd3ff27e82748a06" [[package]] name = "version-compare" @@ -1839,15 +1847,6 @@ dependencies = [ "winapi-util", ] -[[package]] -name = "wasi" -version = "0.14.7+wasi-0.2.4" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "883478de20367e224c0090af9cf5f9fa85bed63a95c1abf3afc5c083ebc06e8c" -dependencies = [ - "wasip2", -] - [[package]] name = "wasip2" version = "1.0.1+wasi-0.2.4" @@ -2047,15 +2046,15 @@ checksum = "712e227841d057c1ee1cd2fb22fa7e5a5461ae8e48fa2ca79ec42cfc1931183f" [[package]] name = "windows-link" -version = "0.2.0" +version = "0.2.1" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "45e46c0661abb7180e7b9c281db115305d49ca1709ab8242adf09666d2173c65" +checksum = "f0805222e57f7521d6a62e36fa9163bc891acd422f971defe97d64e70d0a4fe5" [[package]] name = "windows-sys" -version = "0.61.1" +version = "0.61.2" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "6f109e41dd4a3c848907eb83d5a42ea98b3769495597450cf6d153507b166f0f" +checksum = "ae137229bcbd6cdf0f7b80a31df61766145077ddf49416a728b02cb3921ff3fc" dependencies = [ "windows-link", ] diff --git a/Cargo.toml b/Cargo.toml index 23b3865..b5da12e 100644 --- a/Cargo.toml +++ b/Cargo.toml @@ -5,7 +5,7 @@ edition = "2024" [dependencies] candle-core = { git = "https://github.com/huggingface/candle", rev = "d205fb4" } -modurl = { git = "https://github.com/ModuRL/ModuRL", branch = "implement-determinism" } +modurl = { git = "https://github.com/ModuRL/ModuRL" } tracing = { version = "0.1.37", optional = true } log = { version = "0.4.28", optional = true } box2d-rs = "0.0.4" @@ -26,4 +26,5 @@ tracing = ["dep:tracing"] logging = ["dep:log"] rendering = ["dep:minifb"] cuda = ["candle-core/cuda"] +cudnn = ["candle-core/cudnn"] metal = ["candle-core/metal"] diff --git a/src/classic_control/cartpole.rs b/src/classic_control/cartpole.rs index c182dfe..4889fad 100644 --- a/src/classic_control/cartpole.rs +++ b/src/classic_control/cartpole.rs @@ -470,4 +470,49 @@ mod tests { } } } + + #[cfg(any(feature = "cuda", feature = "metal"))] + #[test] + fn test_cartpole_tensor_determinism() { + #[cfg(feature = "cuda")] + let device = Device::new_cuda(0).unwrap(); + #[cfg(feature = "metal")] + let device = Device::Metal(0); + + let mut last_state: Option = None; + for i in 0..10 { + device.set_seed(42).unwrap(); + let mut env = CartPoleV1::builder().device(&device).build(); + env.reset().unwrap(); + let action_space = env.action_space(); + let mut state = env.state.clone(); + for _ in 0..10 { + let action = action_space.sample(&device).unwrap(); + let StepInfo { + state: next_state, + reward: _, + done, + truncated: _, + } = env.step(action).unwrap(); + state = next_state; + if done { + break; + } + } + if let Some(last) = &last_state { + let state_vec = state.to_vec1::().unwrap(); + let last_vec = last.to_vec1::().unwrap(); + for (a, b) in state_vec.iter().zip(last_vec.iter()) { + assert!( + (a - b) == 0.0, + "States do not match on iteration {}: {} vs {}", + i, + a, + b + ); + } + } + last_state = Some(state); + } + } }