SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2005.05960 · ICML · 2020

Planning to Explore via Self-Supervised World Models

Pieter Abbeel, Deepak Pathak, Ramanan Sekar, Oleh Rybkin, Kostas Daniilidis, Danijar Hafner

arXiv · PDF · Open in the Atlas

Code that ran

4 of 10 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 3 have no contract verdict; 0 failures of our instrument; 6 no recorded run); 1 of them was also run on the host, not in the jail, by the peer-agreement lane that set its level, 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/2005.05960.json · badge: /api/ran/2005.05960.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
ramanans1/plan2explore canonical (classifier label)
classifier basis: classifier_2025
0 ran · 1 no recorded run
kc-ml2/SimpleDreamer community (classifier label)
classifier basis not recorded on the link
3 ran · 2 no recorded run
yusukeurakami/plan2explore-pytorch reimplementation (classifier label)
classifier basis: classifier_2025
1 ran · 3 no recorded run
FunctionStatusWhere it lives
bottle Ran
ran, honoured the contract we drafted
yusukeurakami/plan2explore-pytorch/models.py
code served (permissive licence) · get_code("12a1b11d0e6e3e5b")
How it ran

Ran in Syntology's jail on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned Tensor, ndim 3, dtype family float, shape (2, 3, 9) as a later run recorded it. The image it ran in was not recorded. The comparison behind this sample's level is a different run: the peer-agreement lane ran it again on the host, not in the jail (report dated 2026-09-04T22:37:21Z). 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 torch
import torch.nn as nn

torch.manual_seed(0)

# Create a simple function that takes tensors and processes them
def simple_func(x1, x2):
    """A function that takes two tensors and returns a combined result"""
    # Concatenate along feature dimension
    return torch.cat([x1, x2], dim=-1)

# Create input tensors with shape (batch_size, seq_len, feature_dim)
# Using distinct sizes: batch=2, seq_len=3, feature_dim=4
x1 = torch.randn(2, 3, 4)
x2 = torch.randn(2, 3, 5)

# Create tuple of tensors to pass to bottle
x_tuple = (x1, x2)

ARGS = {
    "f": simple_func,
    "x_tuple": x_tuple
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 3, dtype family float, shape (2, 3, 9) — shape (2, 3, 9) 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
build_network Ran
ran on a synthesized input
kc-ml2/SimpleDreamer/dreamer/utils/utils.py
code served (permissive licence) · get_code("e4d4684737ef6b03")
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 Sequential. 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 torch.nn as nn

torch.manual_seed(0)

ARGS = {
    'input_size': 8,
    'hidden_size': 16,
    'num_layers': 3,
    'activation': 'ReLU',
    'output_size': 4,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Sequential — a Sequential output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Sequential output the recorded ndim 1 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
create_normal_dist Ran
ran on a synthesized input
kc-ml2/SimpleDreamer/dreamer/utils/utils.py
code served (permissive licence) · get_code("5c7a49e9de8098c0")
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 Independent. 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 torch.nn as nn
import torch.nn.functional as F

torch.manual_seed(0)

# Create a small tensor for x
# The function chunks x into mean and std if std is None
# So x should have even last dimension to split into 2 parts
x = torch.randn(2, 8)  # batch_size=2, last_dim=8 (will be chunked to 4 each)

# Create an activation function
activation = torch.nn.Tanh()

# Event shape for Independent distribution
event_shape = 1

ARGS = {
    "x": x,
    "std": None,
    "mean_scale": 1.0,
    "init_std": 0.0,
    "min_std": 0.1,
    "activation": activation,
    "event_shape": event_shape,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Independent — a Independent output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Independent 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
get_env_infos Ran
ran on a synthesized input
kc-ml2/SimpleDreamer/dreamer/envs/envs.py
code served (permissive licence) · get_code("eeeaaa12d116f451")
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 gym
import numpy as np

# Create a mock environment with discrete action space
class MockDiscreteEnv:
    def __init__(self):
        self.observation_space = gym.spaces.Box(low=0, high=1, shape=(4, 3), dtype=np.float32)
        self.action_space = gym.spaces.Discrete(n=5)

env = MockDiscreteEnv()

ARGS = {
    "env": env
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
gym, numpy — 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
Encoder Not yet run
unverified (harvested, no recorded run)
yusukeurakami/plan2explore-pytorch/models.py
code served (permissive licence) · get_code("80cffa53c80556af")
How it ran

no invocation recorded. this sample carries JSON test cases instead of a setup block; get_reference_implementation serves them with the level they back.

ObservationModel Not yet run
unverified (harvested, no recorded run)
yusukeurakami/plan2explore-pytorch/models.py
code served (permissive licence) · get_code("32fa4df355b9a218")
How it ran

no invocation recorded. this sample carries JSON test cases instead of a setup block; get_reference_implementation serves them with the level they back.

TransitionModel Not yet run
unverified (harvested, no recorded run)
yusukeurakami/plan2explore-pytorch/models.py
code served (permissive licence) · get_code("916814eea2a6e02e")
How it ran

no invocation recorded.

cross_entropy_method Not yet run
unverified (harvested, no recorded run)
ramanans1/plan2explore/plan2explore/control/planning.py
code served (permissive licence) · get_code("939b73ec515d6e6d")
How it ran

no invocation recorded.

horizontal_forward Not yet run
unverified (harvested, no recorded run)
kc-ml2/SimpleDreamer/dreamer/utils/utils.py
code served (permissive licence) · get_code("6f0e4af1cf0bca58")
How it ran

no invocation recorded.

make_atari_env Not yet run
unverified (harvested, no recorded run)
kc-ml2/SimpleDreamer/dreamer/envs/envs.py
code served (permissive licence) · get_code("62f8bfe4848e1fbd")
How it ran

no invocation recorded.

Also present in other papers' code

Of 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 10 distinct functions with an identity, 4 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 0 the same month, 2 later) and 6 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
ObservationModel 2 other papers
1 dated earlier, 1 later
1912.01603 (2019-12)
Dream to Control: Learning Behaviors by Latent Imagination
2311.02227 (2023-11)
State-Wise Safe Reinforcement Learning With Pixel Observations
bottle 2 other papers
1 dated earlier, 1 later
1912.01603 (2019-12)
Dream to Control: Learning Behaviors by Latent Imagination
2311.02227 (2023-11)
State-Wise Safe Reinforcement Learning With Pixel Observations
Encoder 1 other paper
1 dated earlier
1912.01603 (2019-12)
Dream to Control: Learning Behaviors by Latent Imagination
TransitionModel
brick of this paper's assembly: entry
1 other paper
1 dated earlier
1912.01603 (2019-12)
Dream to Control: Learning Behaviors by Latent Imagination

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

Reinforcement learning allows solving complex tasks, however, the learning tends to be taskspecific and the sample efficiency remains a challenge. We present Plan2Explore, a selfsupervised reinforcement learning agent that tackles both these challenges through a new approach to self-supervised exploration and fast adaptation to new tasks, which need not be known during exploration. During exploration, unlike prior methods which retrospectively compute the novelty of observations after the agent has already reached them, our agent acts efficiently by leveraging planning to seek out expected future novelty. After exploration, the agent quickly adapts to multiple downstream tasks in a zero or a few-shot manner. We evaluate on challenging control tasks from high-dimensional image inputs. Without any training supervision or taskspecific interaction, Plan2Explore outperforms prior self-supervised exploration methods, and in fact, almost matches the performances oracle which has access to rewards. Videos and code: https://ramanans1.github.io/ plan2explore/

For agents

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

get_harvested_code_for_paper("2005.05960")
get_code_for_paper("2005.05960")
have("2005.05960")

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

curl https://syntology.ai/api/ran/2005.05960.json

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

[![Syntology run record](https://syntology.ai/api/ran/2005.05960.svg)](https://syntology.ai/paper/2005.05960)

Connect an agent — have() is free.