SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1912.08517 · 2019

Distributional Reinforcement Learning for Energy-Based Sequential Models

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 7 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
parshakova/GAMS-for-Data-Efficient-Learning canonical 5 of 7
FunctionStatusWhere it lives
get_batch Ran parshakova/GAMS-for-Data-Efficient-Learning/cycle_r_plambda_pitheta.py
code served (permissive licence) · get_code("ea56b3cd5fdd0135")
get_batch_fsz Ran parshakova/GAMS-for-Data-Efficient-Learning/cycle_r_plambda_pitheta.py
code served (permissive licence) · get_code("744fdcc09a06a4f6")
lsr_div Ran parshakova/GAMS-for-Data-Efficient-Learning/wfsa_n_z.py
code served (permissive licence) · get_code("e649023a04c12420")
lsr_prod Ran parshakova/GAMS-for-Data-Efficient-Learning/wfsa_n_z.py
code served (permissive licence) · get_code("e6e7907969dec1a9")
lsr_sum Ran parshakova/GAMS-for-Data-Efficient-Learning/wfsa_n_z.py
code served (permissive licence) · get_code("847aa97ca2e8344e")
load_data_motif Not yet run parshakova/GAMS-for-Data-Efficient-Learning/cycle_r_plambda_pitheta.py
code served (permissive licence) · get_code("8020c2bca077bb39")
load_data_mult Not yet run parshakova/GAMS-for-Data-Efficient-Learning/r_plambda_pitheta_full.py
code served (permissive licence) · get_code("a697e1cc31400915")

Repositories linked to this paper

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

Abstract

Global Autoregressive Models (GAMs) are a recent proposal [Parshakova et al., CoNLL 2019] for exploiting global properties of sequences for data-efficient learning of seq2seq models. In the first phase of training, an Energy-Based model (EBM) over sequences is derived. This EBM has high representational power, but is unnormalized and cannot be directly exploited for sampling. To address this issue [Parshakova et al., CoNLL 2019] proposes a distillation technique, which can only be applied under limited conditions. By relating this problem to Policy Gradient techniques in RL, but in a \emph{distributional} rather than \emph{optimization} perspective, we propose a general approach applicable to any sequential EBM. Its effectiveness is illustrated on GAM-based experiments.

For agents

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

get_harvested_code_for_paper("1912.08517")
get_code_for_paper("1912.08517")
have("1912.08517")

Connect an agent — have() is free.