SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1910.12179 · 2019

BAIL: Best-Action Imitation Learning for Batch Deep Reinforcement Learning

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 6 functions out of this paper's own repositories and ran 5 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
lanyavik/BAIL canonical 5 of 6
FunctionStatusWhere it lives
L2PenaltyLoss Ran lanyavik/BAIL/spinup/spinup/algos/BAIL/bail_training.py
pointer only (licence: NONE) · get_code("303c000a48de41a3")
calc_ue_valiloss Ran lanyavik/BAIL/spinup/spinup/algos/BAIL/bail_training.py
pointer only (licence: NONE) · get_code("475ab1256cf40ee1")
calculate_mc_gain Ran lanyavik/BAIL/spinup/spinup/algos/BAIL/main_get_mcret.py
pointer only (licence: NONE) · get_code("a8ecbc5e2b2fefaf")
calculate_mc_return_no_aug Ran lanyavik/BAIL/spinup/spinup/algos/BAIL/main_get_mcret.py
pointer only (licence: NONE) · get_code("70d424a5dbf32a39")
evaluate_policy Ran lanyavik/BAIL/spinup/spinup/algos/BAIL/main_static_bail.py
pointer only (licence: NONE) · get_code("c74671448905c5d4")
train_upper_envelope Not yet run lanyavik/BAIL/spinup/spinup/algos/BAIL/bail_training.py
pointer only (licence: NONE) · get_code("72d5b12cffbf9925")

Repositories linked to this paper

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

Abstract

There has recently been a surge in research in batch Deep Reinforcement Learning (DRL), which aims for learning a high-performing policy from a given dataset without additional interactions with the environment. We propose a new algorithm, Best-Action Imitation Learning (BAIL), which strives for both simplicity and performance. BAIL learns a V function, uses the V function to select actions it believes to be high-performing, and then uses those actions to train a policy network using imitation learning. For the MuJoCo benchmark, we provide a comprehensive experimental study of BAIL, comparing its performance to four other batch Q-learning and imitation-learning schemes for a large variety of batch datasets. Our experiments show that BAIL's performance is much higher than the other schemes, and is also computationally much faster than the batch Q-learning schemes.

For agents

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

get_harvested_code_for_paper("1910.12179")
get_code_for_paper("1910.12179")
have("1910.12179")

Connect an agent — have() is free.