SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2010.09635 · 2020

Deep Reinforcement Learning with Population-Coded Spiking Neural Network for Continuous Control

arXiv · PDF · Open in the Atlas

Code that ran

7 of 9 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 4 have no contract verdict; 2 failures of our instrument; 2 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; 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/2010.09635.json · badge: /api/ran/2010.09635.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
combra-lab/pop-spiking-deep-rl canonical (classifier label)
classifier basis: census
7 ran · 2 no recorded run
FunctionStatusWhere it lives
combine_multiple_into_one_int Ran
ran on a synthesized input
combra-lab/pop-spiking-deep-rl/loihi_realization/utility.py
code served (permissive licence) · get_code("deb05398b707eadd")
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 list, ndim 1, dtype family int; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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

torch.manual_seed(0)

# Analyze the function:
# - input_list: a list of integers that will be combined
# - num_bits: number of bits per integer (default 7)
# - overall_bits: total bits available (default 28)
# The function combines multiple small integers into fewer large integers

# With num_bits=7 and overall_bits=28:
# int_per_int_num = 28 // 7 = 4
# So we need input_list to have length that's a multiple of 4

# Create a valid input_list with integers that fit in 7 bits (0-127)
input_list = [5, 10, 15, 20, 3, 7, 11, 14]  # 8 integers, divisible by 4

ARGS = {
    "input_list": input_list,
    "num_bits": 7,
    "overall_bits": 28,
}
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 list, ndim 1, dtype family int — a list output has no array shape of its own; none is stated
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
combined_shape Ran
ran; our contract draft was wrong, not the code
combra-lab/pop-spiking-deep-rl/popsan_drl/popsan_sac/core_cuda.py
pointer only (licence: MIT); the stored copy get_code serves, from yinglunxu/reward_poisoning_attack_drl, is pointer only (licence: NONE) · get_code("57542f87e248db45")
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 yinglunxu/reward_poisoning_attack_drl, 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.

count_vars Ran
ran, honoured the contract we drafted
combra-lab/pop-spiking-deep-rl/popsan_drl/popsan_sac/core_cuda.py
pointer only (licence: MIT); the stored copy get_code serves, from milanganai/milanganai.github.io, is pointer only (licence: NONE) · get_code("4cca5e460067b900")
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 milanganai/milanganai.github.io, 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.

make_env Ran
ran on a synthesized input
combra-lab/pop-spiking-deep-rl/popsan_drl/popsan_ppo/ppo_cuda_norm.py
code served (permissive licence) · get_code("c2985d7efcd097a6")
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 function. 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 gym

ARGS = {
    'env_name': 'CartPole-v1'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
gym — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type function — a function output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a function output the recorded ndim 0 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
mlp Ran
ran; our contract draft was wrong, not the code
combra-lab/pop-spiking-deep-rl/popsan_drl/popsan_sac/core_cuda.py
pointer only (licence: MIT); the stored copy get_code serves, from idsia/policyevaluator, is pointer only (licence: NONE) · get_code("7569e2a512ec417c")
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 idsia/policyevaluator, 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.

pytorch_trained_snn_param_2_loihi_snn_param Ran
ran on a synthesized input
combra-lab/pop-spiking-deep-rl/loihi_realization/utility.py
code served (permissive licence) · get_code("5e58beaffd34b5c3")
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, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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 torch

# Set seed for reproducibility
torch.manual_seed(0)
np.random.seed(0)

# Create small numpy arrays for weight, bias, and vth
# weight: 4x3 matrix (output x input dimensions)
weight = np.random.randn(4, 3) * 10  # Scale to get reasonable values
weight = weight.astype(np.float32)

# bias: 4 elements (one per output neuron)
bias = np.random.randn(4) * 5
bias = bias.astype(np.float32)

# vth: scalar voltage threshold
vth = 1.0

ARGS = {
    "weight": weight,
    "bias": bias,
    "vth": vth
}
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, ndim 1, dtype family float — a tuple output has no array shape of its own; none is stated
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
read_pytorch_network_parameters_4_loihi Ran
ran on a synthesized input
combra-lab/pop-spiking-deep-rl/loihi_realization/utility.py
code served (permissive licence) · get_code("1e2945be1d8c5361")
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 torch.nn as nn

torch.manual_seed(0)

class LearnEncoder(nn.Module):
    def __init__(self):
        super().__init__()
        self.mean = nn.Parameter(torch.randn(4))
        self.std = nn.Parameter(torch.abs(torch.randn(4)) + 0.1)

class FixedEncoder(nn.Module):
    def __init__(self):
        super().__init__()
        self.mean = torch.randn(4).numpy()
        self.var = (torch.abs(torch.randn(4)) + 0.1).numpy() ** 2

class SNNModule(nn.Module):
    def __init__(self):
        super().__init__()
        self.hidden_layers = nn.ModuleList([
            nn.Linear(4, 5),
            nn.Linear(5, 6)
        ])
        self.out_pop_layer = nn.Linear(6, 3)

class DecoderModule(nn.Module):
    def __init__(self):
        super().__init__()
        self.decoder = nn.Linear(3, 2)

class PopSANNetwork(nn.Module):
    def __init__(self, use_learn_encoder=True):
        super().__init__()
        if use_learn_encoder:
            self.encoder = LearnEncoder()
        else:
            self.encoder = FixedEncoder()
        self.snn = SNNModule()
        self.decoder = DecoderModule()

network_learn = PopSANNetwork(use_learn_encoder=True)
network_fixed = PopSANNetwork(use_learn_encoder=False)

ARGS = {
    "network": network_learn,
    "use_learn_encoder": 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 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
test_env Not yet run
unverified (harvested, no recorded run)
combra-lab/pop-spiking-deep-rl/popsan_drl/popsan_ppo/ppo_cuda_norm.py
code served (permissive licence) · get_code("760558af7c4999e1")
How it ran

no invocation recorded.

train_mujoco_ppo Not yet run
unverified (harvested, no recorded run)
combra-lab/pop-spiking-deep-rl/popsan_drl/popsan_ppo/ppo_cuda_norm.py
code served (permissive licence) · get_code("9e151424d7e23786")
How it ran

no invocation recorded.

Also present in other papers' code

Of 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 distinct functions with an identity, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 3 later) and 6 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
combined_shape 14 other papers
3 dated earlier, 11 later
1906.06818 (2019-06)
Stacked Capsule Autoencoders
1912.13465 (2019-12)
Reward-Conditioned Policies
2006.07442 (2020-06)
Self-Imitation Learning via Generalized Lower Bound Q-learning
and 11 more not named here
mlp 12 other papers
3 dated earlier, 9 later · 2 only as an assembly brick
1905.01240 (2019-05)
Information asymmetry in KL-regularized RL
2006.07442 (2020-06)
Self-Imitation Learning via Generalized Lower Bound Q-learning
2006.09359 (2020-06)
AWAC: Accelerating Online Reinforcement Learning with Offline Datasets
and 9 more not named here
count_vars 8 other papers
1 dated earlier, 7 later
2006.07442 (2020-06)
Self-Imitation Learning via Generalized Lower Bound Q-learning
2106.09110 (2021-06)
Safe Reinforcement Learning Using Advantage-Based Intervention
2109.12286 (2021-09)
Stackelberg Actor-Critic: Game-Theoretic Reinforcement Learning Algorithms
and 5 more not named here

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

The energy-efficient control of mobile robots is crucial as the complexity of their real-world applications increasingly involves high-dimensional observation and action spaces, which cannot be offset by limited on-board resources. An emerging non-Von Neumann model of intelligence, where spiking neural networks (SNNs) are run on neuromorphic processors, is regarded as an energy-efficient and robust alternative to the state-of-the-art real-time robotic controllers for low dimensional control tasks. The challenge now for this new computing paradigm is to scale so that it can keep up with real-world tasks. To do so, SNNs need to overcome the inherent limitations of their training, namely the limited ability of their spiking neurons to represent information and the lack of effective learning algorithms. Here, we propose a population-coded spiking actor network (PopSAN) trained in conjunction with a deep critic network using deep reinforcement learning (DRL). The population coding scheme dramatically increased the representation capacity of the network and the hybrid learning combined the training advantages of deep networks with the energy-efficient inference of spiking networks. To show the general applicability of our approach, we integrated it with a spectrum of both on-policy and off-policy DRL algorithms. We deployed the trained PopSAN on Intel's Loihi neuromorphic chip and benchmarked our method against the mainstream DRL algorithms for continuous control. To allow for a fair comparison among all methods, we validated them on OpenAI gym tasks. Our Loihi-run PopSAN consumed 140 times less energy per inference when compared against the deep actor network on Jetson TX2, and had the same level of performance. Our results support the efficiency of neuromorphic controllers and suggest our hybrid RL as an alternative to deep learning, when both energy-efficiency and robustness are important.

For agents

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

get_harvested_code_for_paper("2010.09635")
get_code_for_paper("2010.09635")
have("2010.09635")

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

curl https://syntology.ai/api/ran/2010.09635.json

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

[![Syntology run record](https://syntology.ai/api/ran/2010.09635.svg)](https://syntology.ai/paper/2010.09635)

Connect an agent — have() is free.