SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1907.00456 · 2019

Way Off-Policy Batch Deep Reinforcement Learning of Implicit Human Preferences in Dialog

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 1 functions out of this paper's own repositories and ran 1 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
natashamjaques/neural_chat canonical 1 of 1
FunctionStatusWhere it lives
load_pickle Ran natashamjaques/neural_chat/BatchRL/way_off_policy_batch_rl.py
code served (permissive licence) · get_code("70db7c9cbe9e680d")

Repositories linked to this paper

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

Abstract

Most deep reinforcement learning (RL) systems are not able to learn effectively from off-policy data, especially if they cannot explore online in the environment. These are critical shortcomings for applying RL to real-world problems where collecting data is expensive, and models must be tested offline before being deployed to interact with the environment -- e.g. systems that learn from human interaction. Thus, we develop a novel class of off-policy batch RL algorithms, which are able to effectively learn offline, without exploring, from a fixed batch of human interaction data. We leverage models pre-trained on data as a strong prior, and use KL-control to penalize divergence from this prior during RL training. We also use dropout-based uncertainty estimates to lower bound the target Q-values as a more efficient alternative to Double Q-Learning. The algorithms are tested on the problem of open-domain dialog generation -- a challenging reinforcement learning problem with a 20,000-dimensional action space. Using our Way Off-Policy algorithm, we can extract multiple different reward functions post-hoc from collected human interaction data, and learn effectively from all of these. We test the real-world generalization of these systems by deploying them live to converse with humans in an open-domain setting, and demonstrate that our algorithm achieves significant improvements over prior methods in off-policy batch RL.

For agents

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

get_harvested_code_for_paper("1907.00456")
get_code_for_paper("1907.00456")
have("1907.00456")

Connect an agent — have() is free.