SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2007.03158 · NeurIPS · 2020

The LoCA Regret: A Consistent Metric to Evaluate Model-Based Behavior in Reinforcement Learning

Harm Van Seijen, Hadi Nekoei, Evan Racah, Sarath Chandar, Microsoft Montréal

arXiv · PDF · Open in the Atlas

Code that ran

1 of 2 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 0 failures of our instrument; 1 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/2007.03158.json · badge: /api/ran/2007.03158.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
chandar-lab/LoCA marked official in Papers with Code
Papers with Code archive
1 ran · 0 no recorded run
chandar-lab/LoCA2 community
Papers with Code archive
0 ran · 1 no recorded run
FunctionStatusWhere it lives
ModelBased_agent Ran
ran on a synthesized input · constructed an object; no result was computed
chandar-lab/LoCA/LoCA_tabular/modelbased.py
code served (permissive licence) · get_code("c550ea7498b67f08")
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 an instance of its own class, ModelBased_agent: the run constructed the object and did not call it, so no result was computed. 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 numpy as np

class MockDomain:
    """Mock domain object that satisfies the interface used by ModelBased_agent"""
    
    def __init__(self, num_states=5, num_actions=3, gamma=0.99):
        self.num_states = num_states
        self.num_actions = num_actions
        self.gamma_val = gamma
        self.current_state = 0
        self.task = 0
        self.phase = 'train'
    
    def get_num_states(self):
        return self.num_states
    
    def get_num_actions(self):
        return self.num_actions
    
    def get_gamma(self):
        return self.gamma_val
    
    def get_initial_state(self):
        return 0
    
    def take_action(self, state, action):
        # Return next state and reward
        next_state = (state + 1) % self.num_states
        reward = np.random.rand()
        # Occasionally return -1 to signal episode end
        if np.random.rand() < 0.1:
            next_state = -1
        return next_state, reward
    
    def set_task(self, task_id):
        self.task = task_id
    
    def set_phase(self, phase):
        self.phase = phase
    
    def show_policy(self, policy):
        pass
    
    def show_value(self, value):
        pass


settings = {
    'alpha': 0.1,
    'epsilon': 0.1,
    'transition_epsilon': 0.05,
    'vi': True,
    'model_iterations': 10,
    'q_init': 0.0,
    'max_episode_length': 100,
    'eval_episodes': 5,
    'eval_epsilon': 0.01,
    'eval_max_steps': 50,
}

domain = MockDomain(num_states=5, num_actions=3, gamma=0.99)

ARGS = {
    'settings': settings,
    'domain': domain,
}
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 ModelBased_agent — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a ModelBased_agent 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
LoCAEnv Not yet run
unverified (harvested, no recorded run)
chandar-lab/LoCA2/dyna-exp/core/component/loca_env.py
code served (permissive licence) · get_code("098fafb62e51ed96")
How it ran

no invocation recorded.

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 2026-11-22.

Repositories linked to this paper

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

Abstract

Deep model-based Reinforcement Learning (RL) has the potential to substantially improve the sample-efficiency of deep RL. While various challenges have long held it back, a number of papers have recently come out reporting success with deep model-based methods. This is a great development, but the lack of a consistent metric to evaluate such methods makes it difficult to compare various approaches. For example, the common single-task sample-efficiency metric conflates improvements due to model-based learning with various other aspects, such as representation learning, making it difficult to assess true progress on model-based RL. To address this, we introduce an experimental setup to evaluate model-based behavior of RL methods, inspired by work from neuroscience on detecting model-based behavior in humans and animals. Our metric based on this setup, the Local Change Adaptation (LoCA) regret, measures how quickly an RL method adapts to a local change in the environment. Our metric can identify model-based behavior, even if the method uses a poor representation and provides insight in how close a method's behavior is from optimal model-based behavior. We use our setup to evaluate the model-based behavior of MuZero on a variation of the classic Mountain Car task.

For agents

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

get_harvested_code_for_paper("2007.03158")
get_code_for_paper("2007.03158")
have("2007.03158")

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

curl https://syntology.ai/api/ran/2007.03158.json

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

[![Syntology run record](https://syntology.ai/api/ran/2007.03158.svg)](https://syntology.ai/paper/2007.03158)

Connect an agent — have() is free.