Experience Replay with Likelihood-free Importance Weights

June 23, 2020 Β· Declared Dead Β· πŸ› Conference on Learning for Dynamics & Control

πŸ‘» CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Samarth Sinha, Jiaming Song, Animesh Garg, Stefano Ermon arXiv ID 2006.13169 Category cs.AI: Artificial Intelligence Cross-listed cs.LG Citations 68 Venue Conference on Learning for Dynamics & Control Last Checked 3 months ago
Abstract
The use of past experiences to accelerate temporal difference (TD) learning of value functions, or experience replay, is a key component in deep reinforcement learning. Prioritization or reweighting of important experiences has shown to improve performance of TD learning algorithms.In this work, we propose to reweight experiences based on their likelihood under the stationary distribution of the current policy. Using the corresponding reweighted TD objective, we implicitly encourage small approximation errors on the value function over frequently encountered states. We use a likelihood-free density ratio estimator over the replay buffer to assign the prioritization weights. We apply the proposed approach empirically on two competitive methods, Soft Actor Critic (SAC) and Twin Delayed Deep Deterministic policy gradient (TD3) -- over a suite of OpenAI gym tasks and achieve superior sample complexity compared to other baseline approaches.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

πŸ“œ Similar Papers

In the same crypt β€” Artificial Intelligence

Died the same way β€” πŸ‘» Ghosted