SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2105.10682 · 2021

Feasible Actor-Critic: Constrained Reinforcement Learning for Ensuring Statewise Safety

arXiv · PDF · Open in the Atlas

Code that ran

3 of 6 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 2 have no contract verdict; 0 failures of our instrument; 3 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/2105.10682.json · badge: /api/ran/2105.10682.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
mahaitongdae/Feasible-Actor-Critic canonical (classifier label)
classifier basis: census
3 ran · 3 no recorded run
FunctionStatusWhere it lives
help_func Ran
ran on a synthesized input
mahaitongdae/Feasible-Actor-Critic/ploter.py
code served (permissive licence) · get_code("6d7182a8d3f335dd")
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

ARGS = {
    'env': 'path_tracking_env'
}
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
min_n Ran
ran on a synthesized input
mahaitongdae/Feasible-Actor-Critic/ploter.py
code served (permissive licence) · get_code("ce7191c627d919b5")
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)

# The function min_n takes inp_list and n as parameters
# It sorts inp_list and returns the first n elements
# inp_list should be a list of comparable items
# n should be an integer

inp_list = [5, 2, 8, 1, 9, 3, 7, 4]
n = 3

ARGS = {
    "inp_list": inp_list,
    "n": n
}
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
update_mean_var_count_from_moments Ran
ran, honoured the contract we drafted
mahaitongdae/Feasible-Actor-Critic/preprocessor.py
pointer only (licence: MIT); the stored copy get_code serves, from joonleesky/train-procgen-pytorch, is pointer only (licence: NONE) · get_code("3ebb420a5d10cc64")
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 joonleesky/train-procgen-pytorch, 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.

built_parser Not yet run
unverified (harvested, no recorded run)
mahaitongdae/Feasible-Actor-Critic/train_script4fsac.py
code served (permissive licence) · get_code("8e77d175d25461f7")
How it ran

no invocation recorded.

built_parser Not yet run
unverified (harvested, no recorded run)
mahaitongdae/Feasible-Actor-Critic/train_scripts/train_script4fsac_with_trained_model.py
code served (permissive licence) · get_code("7fb1719dd18effc4")
How it ran

no invocation recorded.

compute_convergence_speed Not yet run
unverified (harvested, no recorded run)
mahaitongdae/Feasible-Actor-Critic/ploter.py
code served (permissive licence) · get_code("0b9cc3b9817b83d6")
How it ran

no invocation recorded.

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 1 the same month, 1 later) and 5 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
update_mean_var_count_from_moments 8 other papers
3 dated earlier, 1 the same month, 4 later · 1 only as an assembly brick
1901.09184 (2019-01)
Action Robust Reinforcement Learning and Applications in Continuous Control
1912.01588 (2019-12)
Leveraging Procedural Generation to Benchmark Reinforcement Learning
2006.14171 (2020-06)
A Closer Look at Invalid Action Masking in Policy Gradient 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 safety constraints commonly used by existing safe reinforcement learning (RL) methods are defined only on expectation of initial states, but allow each certain state to be unsafe, which is unsatisfying for real-world safety-critical tasks. In this paper, we introduce the feasible actor-critic (FAC) algorithm, which is the first model-free constrained RL method that considers statewise safety, e.g, safety for each initial state. We claim that some states are inherently unsafe no matter what policy we choose, while for other states there exist policies ensuring safety, where we say such states and policies are feasible. By constructing a statewise Lagrange function available on RL sampling and adopting an additional neural network to approximate the statewise Lagrange multiplier, we manage to obtain the optimal feasible policy which ensures safety for each feasible state and the safest possible policy for infeasible states. Furthermore, the trained multiplier net can indicate whether a given state is feasible or not through the statewise complementary slackness condition. We provide theoretical guarantees that FAC outperforms previous expectation-based constrained RL methods in terms of both constraint satisfaction and reward optimization. Experimental results on both robot locomotive tasks and safe exploration tasks verify the safety enhancement and feasibility interpretation of the proposed method.

For agents

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

get_harvested_code_for_paper("2105.10682")
get_code_for_paper("2105.10682")
have("2105.10682")

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

curl https://syntology.ai/api/ran/2105.10682.json

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

[![Syntology run record](https://syntology.ai/api/ran/2105.10682.svg)](https://syntology.ai/paper/2105.10682)

Connect an agent — have() is free.