SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2110.04698 · 2021

A Closer Look at Advantage-Filtered Behavioral Cloning in High-Noise Datasets

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 5 functions out of this paper's own repositories and ran 3 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
jakegrigsby/cc-afbc canonical 3 of 5
FunctionStatusWhere it lives
get_linear_schedule Ran jakegrigsby/cc-afbc/filters.py
code served (permissive licence) · get_code("63bb6952481500e6")
robosuite_action_adjustment Ran jakegrigsby/cc-afbc/rl_utils/envs.py
code served (permissive licence) · get_code("ab198159e66084fd")
unique Ran jakegrigsby/cc-afbc/rl_utils/replay.py
code served (permissive licence) · get_code("cf11c744c61b2185")
highway_env Not yet run jakegrigsby/cc-afbc/rl_utils/envs.py
code served (permissive licence) · get_code("771d49bb23e04b6c")
load_gym Not yet run jakegrigsby/cc-afbc/rl_utils/envs.py
code served (permissive licence) · get_code("d13ad67924e983b5")

Repositories linked to this paper

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

Abstract

Recent Offline Reinforcement Learning methods have succeeded in learning high-performance policies from fixed datasets of experience. A particularly effective approach learns to first identify and then mimic optimal decision-making strategies. Our work evaluates this method's ability to scale to vast datasets consisting almost entirely of sub-optimal noise. A thorough investigation on a custom benchmark helps identify several key challenges involved in learning from high-noise datasets. We re-purpose prioritized experience sampling to locate expert-level demonstrations among millions of low-performance samples. This modification enables offline agents to learn state-of-the-art policies in benchmark tasks using datasets where expert actions are outnumbered nearly 65:1.

For agents

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

get_harvested_code_for_paper("2110.04698")
get_code_for_paper("2110.04698")
have("2110.04698")

Connect an agent — have() is free.