α
Research
Alpha Leak
Conferences
Topics
Top Authors
Rankings
Browse All
EN
中
Home
/
Authors
/
Pablo Samuel Castro
Pablo Samuel Castro
16
papers
1,600
total citations
papers (16)
Deep Reinforcement Learning at the Edge of the Statistical Precipice
NEURIPS 2021
arXiv
814
citations
Minigrid & Miniworld: Modular & Customizable Reinforcement Learning Environments for Goal-Oriented Tasks
NEURIPS 2023
arXiv
318
citations
Stop Regressing: Training Value Functions via Classification for Scalable Deep RL
ICML 2024
arXiv
107
citations
Reincarnating Reinforcement Learning: Reusing Prior Computation to Accelerate Progress
NEURIPS 2022
arXiv
85
citations
The Difficulty of Passive Learning in Deep Reinforcement Learning
NEURIPS 2021
arXiv
68
citations
Mixtures of Experts Unlock Parameter Scaling for Deep RL
ICML 2024
arXiv
64
citations
MICo: Improved representations via sampling-based state similarity for Markov decision processes
NEURIPS 2021
arXiv
44
citations
In value-based deep reinforcement learning, a pruned network is a good network
ICML 2024
arXiv
33
citations
Small batch deep reinforcement learning
NEURIPS 2023
arXiv
28
citations
Stable Gradients for Stable Learning at Scale in Deep Reinforcement Learning
NEURIPS 2025
arXiv
10
citations
The Impact of On-Policy Parallelized Data Collection on Deep Reinforcement Learning Networks
ICML 2025
arXiv
7
citations
Mitigating Plasticity Loss in Continual Reinforcement Learning by Reducing Churn
ICML 2025
arXiv
7
citations
Studying the Interplay Between the Actor and Critic Representations in Reinforcement Learning
ICLR 2025
arXiv
5
citations
Measure gradients, not activations! Enhancing neuronal activity in deep reinforcement learning
NEURIPS 2025
arXiv
4
citations
The Courage to Stop: Overcoming Sunk Cost Fallacy in Deep Reinforcement Learning
ICML 2025
arXiv
4
citations
Adaptive Accompaniment with ReaLchords
ICML 2024
arXiv
2
citations