SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2107.00848 · 2021

Systematic Evaluation of Causal Discovery in Visual Model Based Reinforcement Learning

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 14 functions out of this paper's own repositories and ran 0 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
dido1998/CausalMBRL canonical 0 of 14
FunctionStatusWhere it lives
contrastive_loss Not yet run dido1998/CausalMBRL/cswm/models/losses.py
code served (permissive licence) · get_code("4d34bf6b39947167")
crop_normalize Not yet run dido1998/CausalMBRL/data_gen/env.py
code served (permissive licence) · get_code("962a1bc92a316173")
diamond Not yet run dido1998/CausalMBRL/envs/chemistry_env.py
code served (permissive licence) · get_code("c384344f5bf6ceff")
energy Not yet run dido1998/CausalMBRL/cswm/models/losses.py
code served (permissive licence) · get_code("1dd9382c7e7b0741")
fig2rgb_array Not yet run dido1998/CausalMBRL/envs/block_pushing.py
code served (permissive licence) · get_code("730a49531670258a")
generate_episode Not yet run dido1998/CausalMBRL/data_gen/env.py
code served (permissive licence) · get_code("9f5f70ce63ff3076")
get_cmap Not yet run dido1998/CausalMBRL/cswm/utils.py
code served (permissive licence) · get_code("3ad1b4670dbfe46d")
image_loss Not yet run dido1998/CausalMBRL/cswm/models/losses.py
code served (permissive licence) · get_code("59b0d3a48965d4ca")
load_dict_h5py Not yet run dido1998/CausalMBRL/cswm/utils.py
code served (permissive licence) · get_code("8e0583d19b2de35a")
load_list_dict_h5py Not yet run dido1998/CausalMBRL/cswm/utils.py
code served (permissive licence) · get_code("15362d0dcd6a886f")
random_dag Not yet run dido1998/CausalMBRL/envs/chemistry_env.py
code served (permissive licence) · get_code("3d2f99bfac8446e8")
square Not yet run dido1998/CausalMBRL/envs/block_pushing.py
code served (permissive licence) · get_code("056c87133dcaa814")
triangle Not yet run dido1998/CausalMBRL/envs/block_pushing.py
code served (permissive licence) · get_code("d15591e079c2aced")
try_generate_episode Not yet run dido1998/CausalMBRL/data_gen/env.py
code served (permissive licence) · get_code("33719af496938230")

Repositories linked to this paper

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

Abstract

Inducing causal relationships from observations is a classic problem in machine learning. Most work in causality starts from the premise that the causal variables themselves are observed. However, for AI agents such as robots trying to make sense of their environment, the only observables are low-level variables like pixels in images. To generalize well, an agent must induce high-level variables, particularly those which are causal or are affected by causal variables. A central goal for AI and causality is thus the joint discovery of abstract representations and causal structure. However, we note that existing environments for studying causal induction are poorly suited for this objective because they have complicated task-specific causal graphs which are impossible to manipulate parametrically (e.g., number of nodes, sparsity, causal chain length, etc.). In this work, our goal is to facilitate research in learning representations of high-level variables as well as causal structures among them. In order to systematically probe the ability of methods to identify these variables and structures, we design a suite of benchmarking RL environments. We evaluate various representation learning algorithms from the literature and find that explicitly incorporating structure and modularity in models can help causal induction in model-based reinforcement learning.

For agents

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

get_harvested_code_for_paper("2107.00848")
get_code_for_paper("2107.00848")
have("2107.00848")

Connect an agent — have() is free.