mlsanityData to 7 Oct 2026

Where2Start: Leveraging initial States for Robust and Sample-Efficient Reinforcement Learning

arXiv 2311.15089 ↗First posted 25 Nov 2023cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

The reinforcement learning algorithms that focus on how to compute the gradient and choose next actions, are effectively improved the performance of the agents. However, these algorithms are environment-agnostic. This means that the algorithms did not use the knowledge that has been captured by trajectory. This poses that the algorithms should sample many trajectories to train the model. By considering the essence of environment and how much the agent learn from each scenario in that environment, the strategy of the learning procedure can be changed. The strategy retrieves more informative trajectories, so the agent can learn with fewer trajectory sample. We propose Where2Start algorithm that selects the initial state so that the agent has more instability in vicinity of that state. We show that this kind of selection decreases number of trajectories that should be sampled that the agent reach to acceptable reward. Our experiments shows that Where2Start can improve sample efficiency up to 8 times. Also Where2Start can combined with most of state-of-the-art algorithms and improve that robustness and sample efficiency significantly.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 15 of its 23 references that are in the map. First posted on arXiv 25 Nov 2023.

Builds on

15 of 23 references.

References · 15

  1. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,635
  2. 2017Robust Adversarial Reinforcement Learningcited by 439
  3. 2017Adversarial Attacks on Neural Network Policiescited by 314
  4. 2019Go-Explore: a New Approach for Hard-Exploration Problemscited by 207
  5. 2018An Introduction to Deep Reinforcement Learningcited by 201
  6. 2017Reverse Curriculum Generation for Reinforcement Learningcited by 185
  7. 2016Deep Reinforcement Learning from Self-Play in Imperfect-Information Gamescited by 153
  8. 2017Robust Deep Reinforcement Learning with Adversarial Attackscited by 152
  9. 2018Learning Montezuma's Revenge from a Single Demonstrationcited by 76
  10. 2021Twice regularized MDPs and the equivalence between robustness and regularizationcited by 46
  11. 2020Robust Reinforcement Learning via Adversarial training with Langevin Dynamicscited by 45
  12. 2019Beyond Confidence Regions: Tight Bayesian Ambiguity Sets for Robust MDPscited by 37
3 more
  1. 2019Improved Robustness and Safety for Autonomous Vehicle Control with Adversarial Reinforcement Learningcited by 23
  2. 2020Entropic Risk Constrained Soft-Robust Policy Optimizationcited by 3
  3. 2021Improving Robustness of Deep Reinforcement Learning Agents: Environment Attack based on the Critic Networkcited by 3

Built on by

Not cited yet.