SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2307.14993 · 2023

Thinker: Learning to Plan and Act

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 0 have no contract verdict; 2 failures of our instrument; 0 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/2307.14993.json · badge: /api/ran/2307.14993.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
stephen-chung-mh/thinker canonical (classifier label)
classifier basis: classifier_2025
2 ran · 0 no recorded run
FunctionStatusWhere it lives
plot_multi_gym_env_out Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
stephen-chung-mh/thinker/thinker/visual.py
code served (permissive licence) · get_code("d570fc541bc96cc3")
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) and returned Figure. 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

# Create sample gym environment outputs
# The function expects xs to be a list of images with shape (C, H, W)
# where C is channels, H is height, W is width
# It transposes to (H, W, C) for imshow

# Create 7 sample images (3 channels, 32x32 pixels each)
xs = [
    np.random.randint(0, 256, size=(3, 32, 32), dtype=np.uint8)
    for _ in range(7)
]

# Create optional titles
titles = [f"Environment {i+1}" for i in range(7)]

ARGS = {
    "xs": xs,
    "titles": titles,
    "col_n": 5,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
matplotlib, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Figure — a Figure output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Figure 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
print_im_actions Ran
ran; our contract draft was wrong, not the code
stephen-chung-mh/thinker/thinker/visual.py
code served (permissive licence) · get_code("b08cd2f542667fe6")
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) and returned list, 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 torch

torch.manual_seed(0)

# Construct im_dict with 'pri' and 'cur_reset' keys
# 'pri' should be a tensor of actions (discrete indices or continuous vectors)
# 'cur_reset' should be a tensor of reset flags
im_dict = {
    'pri': torch.tensor([0, 1, 2, 0, 1]),  # 5 discrete actions
    'cur_reset': torch.tensor([0, 0, 1, 0, 1])  # reset flags
}

# action_meanings: list of strings for discrete action lookup
action_meanings = ['move_left', 'move_right', 'jump', 'crouch', 'idle']

# real_action: can be either a discrete action (scalar tensor) or continuous (1D tensor)
real_action = torch.tensor(2)  # scalar tensor for discrete action

ARGS = {
    'im_dict': im_dict,
    'action_meanings': action_meanings,
    'real_action': real_action,
    'print_stat': False
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
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 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 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

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

We propose the Thinker algorithm, a novel approach that enables reinforcement learning agents to autonomously interact with and utilize a learned world model. The Thinker algorithm wraps the environment with a world model and introduces new actions designed for interacting with the world model. These model-interaction actions enable agents to perform planning by proposing alternative plans to the world model before selecting a final action to execute in the environment. This approach eliminates the need for handcrafted planning algorithms by enabling the agent to learn how to plan autonomously and allows for easy interpretation of the agent's plan with visualization. We demonstrate the algorithm's effectiveness through experimental results in the game of Sokoban and the Atari 2600 benchmark, where the Thinker algorithm achieves state-of-the-art performance and competitive results, respectively. Visualizations of agents trained with the Thinker algorithm demonstrate that they have learned to plan effectively with the world model to select better actions. Thinker is the first work showing that an RL agent can learn to plan with a learned world model in complex environments.

For agents

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

get_harvested_code_for_paper("2307.14993")
get_code_for_paper("2307.14993")
have("2307.14993")

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

curl https://syntology.ai/api/ran/2307.14993.json

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

[![Syntology run record](https://syntology.ai/api/ran/2307.14993.svg)](https://syntology.ai/paper/2307.14993)

Connect an agent — have() is free.