SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2602.18277 · 2026

PRISM: Parallel Reward Integration with Symmetry for MORL

Fengxiang He, Zheng Xu, Kejiang Qian, Finn Van Der Knaap

arXiv · PDF · Open in the Atlas

Code that ran

5 of 5 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 4 failures of our instrument; 0 no recorded run), measured 2026-11-22; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2602.18277.json · badge: /api/ran/2602.18277.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
EVIEHub/PRISM canonical (classifier label)
classifier basis: census
5 ran · 0 no recorded run
FunctionStatusWhere it lives
collate_trajectories Ran
ran; our contract draft was wrong, not the code
EVIEHub/PRISM/code/src/reward_shaping/reward_model.py
code served (permissive licence) · get_code("f1709b457c683d69")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np
from torch.nn.utils.rnn import pad_sequence

torch.manual_seed(0)

# Create a simple normalizer function that normalizes features
def simple_normalizer(features_array):
    """Normalize features to zero mean and unit variance"""
    mean = features_array.mean(axis=0, keepdims=True)
    std = features_array.std(axis=0, keepdims=True) + 1e-8
    return (features_array - mean) / std

# Create batch data: list of (features, targets) tuples
# Each item has variable-length trajectory of feature vectors and a target tensor
batch = [
    # First trajectory: 3 steps, each with 4-dim features
    (
        [np.array([1.0, 2.0, 3.0, 4.0]), 
         np.array([2.0, 3.0, 4.0, 5.0]),
         np.array([3.0, 4.0, 5.0, 6.0])],
        torch.tensor([0.5, 1.5], dtype=torch.float32)
    ),
    # Second trajectory: 2 steps, each with 4-dim features
    (
        [np.array([5.0, 6.0, 7.0, 8.0]),
         np.array([6.0, 7.0, 8.0, 9.0])],
        torch.tensor([2.5, 3.5], dtype=torch.float32)
    ),
]

ARGS = {
    "batch": batch,
    "normalizer": simple_normalizer
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
huber Ran
ran; our contract draft was wrong, not the code
EVIEHub/PRISM/code/morl_baselines/common/networks.py
pointer only (licence: MIT); the stored copy get_code serves, from arnaudlequen/PQLRM, is pointer only (licence: NONE) · get_code("5f99e218ffb1f571")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from arnaudlequen/PQLRM, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

load_data_from_runs Ran
ran, honoured the contract we drafted
EVIEHub/PRISM/code/plot_single_policy.py
code served (permissive licence) · get_code("c8d2b03c56785e02")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned ndarray, ndim 2, dtype family float, shape (3, 5) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np
import tempfile
from pathlib import Path
import argparse

# Create temporary directory structure with .npz files
temp_dir = tempfile.mkdtemp()
model_dir = Path(temp_dir) / "test_model"
model_dir.mkdir(parents=True, exist_ok=True)

# Create sample .npz files with data
for run_idx in range(3):
    npz_path = model_dir / f"run_{run_idx}.npz"
    # Create sample data: shape (5, 8) - 5 samples, 8 features
    sample_data = np.random.randn(5, 8)
    np.savez(npz_path, metrics=sample_data)

# Create argparse.Namespace with required attributes
args = argparse.Namespace(
    data_key='metrics',
    group_by_model=None,
    group_size=2
)

ARGS = {
    'model_path': model_dir,
    'args': args
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 2, dtype family float, shape (3, 5) — shape (3, 5) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
mlp Ran
ran; our contract draft was wrong, not the code
EVIEHub/PRISM/code/morl_baselines/common/networks.py
pointer only (licence: MIT); the stored copy get_code serves, from arnaudlequen/PQLRM, is pointer only (licence: NONE) · get_code("0be43fb4202eab1d")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from arnaudlequen/PQLRM, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

mlp_no_bias Ran
ran; our contract draft was wrong, not the code
EVIEHub/PRISM/code/morl_baselines/common/networks.py
code served (permissive licence) · get_code("1fc094270c2db881")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Sequential. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn
from typing import List, Type

torch.manual_seed(0)

ARGS = {
    "input_dim": 4,
    "output_dim": 3,
    "net_arch": [8, 6],
    "activation_fn": nn.ReLU,
    "drop_rate": 0.1,
    "layer_norm": True,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Sequential — a Sequential output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Sequential output the recorded ndim 1 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 distinct functions with an identity, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 2 later) and 3 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
huber 2 other papers
1 dated earlier, 1 later
2311.12495 (2023-11)
Multi-Objective Reinforcement Learning Based on Decomposition: A Taxonomy and Framework
2606.19134 (2026-06)
Pareto Q-Learning with Reward Machines
mlp 2 other papers
1 dated earlier, 1 later
2311.12495 (2023-11)
Multi-Objective Reinforcement Learning Based on Decomposition: A Taxonomy and Framework
2606.19134 (2026-06)
Pareto Q-Learning with Reward Machines

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

This work studies heterogeneous Multi-Objective Reinforcement Learning (MORL), where objectives can differ sharply in temporal frequency. Such heterogeneity allows dense objectives to dominate learning, while sparse long-horizon rewards receive weak credit assignment, leading to poor sample efficiency. We propose a Parallel Reward Integration with Symmetry (PRISM) algorithm that enforces reflectional symmetry as an inductive bias in aligning reward channels. PRISM introduces ReSymNet, a theory-motivated model that reconciles temporal-frequency mismatches across objectives, using residual blocks to learn a scaled opportunity value that accelerates exploration while preserving the optimal policy. We also propose SymReg, a reflectional equivariance regulariser that enforces agent mirroring and constrains policy search to a reflection-equivariant subspace. This restriction provably reduces hypothesis complexity and improves generalisation. Across MuJoCo benchmarks, PRISM consistently outperforms both a sparse-reward baseline and an oracle trained with full dense rewards, improving Pareto coverage and distributional balance: it achieves hypervolume gains exceeding 100% over the baseline and up to 32% over the oracle. The code is at https://github.com/EVIEHub/PRISM.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2602.18277")
get_code_for_paper("2602.18277")
have("2602.18277")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2602.18277.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2602.18277.svg)](https://syntology.ai/paper/2602.18277)

Connect an agent — have() is free.