SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2004.07804 · ICML · 2020

A Game Theoretic Framework for Model Based Reinforcement Learning

Igor Mordatch, Aravind Rajeswaran, Vikash Kumar

arXiv · PDF · Open in the Atlas

Code that ran

2 of 2 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; 0 honoured the contract we drafted, 0 violated it and 2 have no contract verdict; 0 failures of our instrument; 0 no recorded run), measured 2026-11-21; 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/2004.07804.json · badge: /api/ran/2004.07804.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
aravindr93/mjrl canonical (classifier label)
classifier basis: census
2 ran · 0 no recorded run
FunctionStatusWhere it lives
config_tqdm Ran
ran on a synthesized input
aravindr93/mjrl/mjrl/algos/behavior_cloning.py
code served (permissive licence) · get_code("92c04e6a292f8962")
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 tqdm. 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
from tqdm import tqdm

torch.manual_seed(0)

# The function takes range_inp and suppress_tqdm
# range_inp is used with tqdm() or returned directly, so it should be iterable
# suppress_tqdm is a boolean flag

range_inp = range(5)
suppress_tqdm = False

ARGS = {
    "range_inp": range_inp,
    "suppress_tqdm": suppress_tqdm,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch, tqdm — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tqdm — a tqdm output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a tqdm 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
fit_data Ran
ran on a synthesized input
aravindr93/mjrl/mjrl/utils/optimize_model.py
code served (permissive licence) · get_code("974cb9a78de718f0")
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 2, dtype family float; no output shape is stated. It ran in syntology-harvest-sandbox:v5-deps (sha256:6a292aa1aed1) at 2026-09-27T00:55:05Z. 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 torch.nn as nn
import torch.optim as optim
import numpy as np

torch.manual_seed(0)
np.random.seed(0)

# Define a simple model
class SimpleModel(nn.Module):
    def __init__(self):
        super(SimpleModel, self).__init__()
        self.linear = nn.Linear(4, 3)
    
    def forward(self, x):
        return self.linear(x)

# Create model instance
model = SimpleModel()

# Create small tensors (batch_size=2, input_dim=4, output_dim=3)
x = torch.randn(10, 4)  # 10 samples, 4 features
y = torch.randn(10, 3)  # 10 samples, 3 targets

# Create optimizer
optimizer = optim.SGD(model.parameters(), lr=0.01)

# Create loss function
loss_func = nn.MSELoss()

# Set batch size and epochs
batch_size = 2
epochs = 2

ARGS = {
    'model': model,
    'x': x,
    'y': y,
    'optimizer': optimizer,
    'loss_func': loss_func,
    'batch_size': batch_size,
    'epochs': epochs
}
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 2, dtype family float — 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 syntology-harvest-sandbox:v5-deps (sha256:6a292aa1aed1); 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 2 samples lifted from this paper's linked repositories, 2 carry a function identity and 0 do not. Of the 2 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 2 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.

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 2026-11-21.

Repositories linked to this paper

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

Abstract

Designing stable and efficient algorithms for model-based reinforcement learning (MBRL) with function approximation has remained challenging despite growing interest in the field. To help expose the practical challenges in MBRL and simplify algorithm design from the lens of abstraction, we develop a new framework that casts MBRL as a game between: (1) a policy player, which attempts to maximize rewards under the learned model; (2) a model player, which attempts to fit the real-world data collected by the policy player. We show that a near-optimal policy for the environment can be obtained by finding an approximate equilibrium for aforementioned game, and we develop two families of algorithms to find the game equilibrium by drawing upon ideas from Stackelberg games. Experimental studies suggest that the proposed algorithms achieve state of the art sample efficiency, match the asymptotic performance of model-free policy gradient, and scale gracefully to high-dimensional tasks like dexterous hand manipulation. Project page: https:// sites.google.com/view/mbrl-game.

For agents

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

get_harvested_code_for_paper("2004.07804")
get_code_for_paper("2004.07804")
have("2004.07804")

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

curl https://syntology.ai/api/ran/2004.07804.json

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

[![Syntology run record](https://syntology.ai/api/ran/2004.07804.svg)](https://syntology.ai/paper/2004.07804)

Connect an agent — have() is free.