SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2106.03273 · 2021

Control-Oriented Model-Based Reinforcement Learning with Implicit Differentiation

arXiv · PDF · Open in the Atlas

Code that ran

3 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; 0 honoured the contract we drafted, 0 violated it and 2 have no contract verdict; 1 failure 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/2106.03273.json · badge: /api/ran/2106.03273.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
evgenii-nikishin/omd canonical (classifier label)
classifier basis: census
3 ran · 2 no recorded run
FunctionStatusWhere it lives
default_init Ran
ran; our contract draft was wrong, not the code
evgenii-nikishin/omd/mujoco/jax_rl/networks/common.py
code served (permissive licence) · get_code("1bd2d556360ac9c9")
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 jax.numpy as jnp
import flax.linen as nn

ARGS = {
    "scale": jnp.sqrt(2)
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
flax, jax — 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
evaluate Ran
ran on a synthesized input
evgenii-nikishin/omd/cartpole/utils.py
code served (permissive licence) · get_code("580e68a39efc066b")
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 float, ndim 0, dtype family float, shape () 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 jax
import jax.numpy as jnp
import numpy as np

# Create a minimal agent with required interface
class SimpleAgent:
    def __init__(self):
        self.params_Q = jnp.array([0.1, 0.2, 0.3, 0.4])
    
    def act(self, params, obs, rng):
        # Returns an action as a scalar that can be .item()'d
        action_val = jnp.sum(params * obs) + jax.random.normal(rng)
        return jnp.asarray(action_val)

# Create a minimal environment with required interface
class SimpleEnv:
    def __init__(self):
        self.obs_dim = 4
        self.action_dim = 3
        self.step_count = 0
        self.max_steps = 5
    
    def reset(self):
        self.step_count = 0
        return jnp.ones(self.obs_dim, dtype=jnp.float32)
    
    def step(self, action):
        self.step_count += 1
        obs = jnp.ones(self.obs_dim, dtype=jnp.float32) * 0.5
        reward = 1.0
        done = self.step_count >= self.max_steps
        info = {}
        return obs, reward, done, info

# Create instances
agent = SimpleAgent()
eval_env = SimpleEnv()
rng = jax.random.PRNGKey(42)

ARGS = {
    "agent": agent,
    "eval_env": eval_env,
    "rng": rng,
    "num_eval_episodes": 2
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
jax, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float, ndim 0, dtype family float, shape () — shape () 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
evaluate Ran
ran on a synthesized input
evgenii-nikishin/omd/mujoco/jax_rl/evaluation.py
code served (permissive licence) · get_code("09dd14441f8afd51")
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 dict. 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
import numpy as np
import flax.linen as nn
from typing import Dict


class DummyAgent(nn.Module):
    """Minimal agent that implements sample_actions method."""
    
    def sample_actions(self, observation, temperature=0.0):
        """Return a dummy action based on observation."""
        # Return a simple scalar action
        return 0


class DummyEnv(gym.Env):
    """Minimal gym environment for testing."""
    
    def __init__(self):
        self.observation_space = gym.spaces.Box(low=0, high=1, shape=(4,), dtype=np.float32)
        self.action_space = gym.spaces.Discrete(2)
        self.step_count = 0
        self.max_steps = 3
    
    def reset(self):
        self.step_count = 0
        return np.array([0.1, 0.2, 0.3, 0.4], dtype=np.float32)
    
    def step(self, action):
        self.step_count += 1
        observation = np.array([0.1, 0.2, 0.3, 0.4], dtype=np.float32)
        reward = 1.0
        done = self.step_count >= self.max_steps
        info = {
            'episode': {
                'return': 3.0,
                'length': self.step_count
            }
        }
        return observation, reward, done, info


agent = DummyAgent()
env = DummyEnv()
num_episodes = 2

ARGS = {
    'agent': agent,
    'env': env,
    'num_episodes': num_episodes
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
flax, gym, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
root_solve Not yet run
unverified (harvested, no recorded run)
evgenii-nikishin/omd/cartpole/utils.py
code served (permissive licence) · get_code("7228e3fe72fe5ce1")
How it ran

no invocation recorded.

root_solve_fwd Not yet run
unverified (harvested, no recorded run)
evgenii-nikishin/omd/cartpole/utils.py
code served (permissive licence) · get_code("3f2a540c4e621bac")
How it ran

no invocation recorded.

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, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 1 later) and 4 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
default_init 8 other papers
1 dated earlier, 7 later
1812.05905 (2018-12)
Soft Actor-Critic Algorithms and Applications
2206.01079 (2022-06)
When does return-conditioned supervised learning work for offline reinforcement learning?
2301.12842 (2023-01)
Direct Preference-based Policy Optimization without Reward Modeling
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 shortcomings of maximum likelihood estimation in the context of model-based reinforcement learning have been highlighted by an increasing number of papers. When the model class is misspecified or has a limited representational capacity, model parameters with high likelihood might not necessarily result in high performance of the agent on a downstream control task. To alleviate this problem, we propose an end-to-end approach for model learning which directly optimizes the expected returns using implicit differentiation. We treat a value function that satisfies the Bellman optimality operator induced by the model as an implicit function of model parameters and show how to differentiate the function. We provide theoretical and empirical evidence highlighting the benefits of our approach in the model misspecification regime compared to likelihood-based methods.

For agents

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

get_harvested_code_for_paper("2106.03273")
get_code_for_paper("2106.03273")
have("2106.03273")

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

curl https://syntology.ai/api/ran/2106.03273.json

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

[![Syntology run record](https://syntology.ai/api/ran/2106.03273.svg)](https://syntology.ai/paper/2106.03273)

Connect an agent — have() is free.