Pablo Samuel Castro

papers

1,600

total citations

papers (16)

Deep Reinforcement Learning at the Edge of the Statistical Precipice

NEURIPS 2021arXiv

814

citations

Minigrid & Miniworld: Modular & Customizable Reinforcement Learning Environments for Goal-Oriented Tasks

NEURIPS 2023arXiv

318

citations

Stop Regressing: Training Value Functions via Classification for Scalable Deep RL

ICML 2024arXiv

107

citations

Reincarnating Reinforcement Learning: Reusing Prior Computation to Accelerate Progress

NEURIPS 2022arXiv

citations

The Difficulty of Passive Learning in Deep Reinforcement Learning

NEURIPS 2021arXiv

citations

Mixtures of Experts Unlock Parameter Scaling for Deep RL

ICML 2024arXiv

citations

MICo: Improved representations via sampling-based state similarity for Markov decision processes

NEURIPS 2021arXiv

citations

The Impact of On-Policy Parallelized Data Collection on Deep Reinforcement Learning Networks

ICML 2025arXiv

citations

Mitigating Plasticity Loss in Continual Reinforcement Learning by Reducing Churn

ICML 2025arXiv

citations

Studying the Interplay Between the Actor and Critic Representations in Reinforcement Learning

ICLR 2025arXiv

citations

Measure gradients, not activations! Enhancing neuronal activity in deep reinforcement learning

NEURIPS 2025arXiv

citations

The Courage to Stop: Overcoming Sunk Cost Fallacy in Deep Reinforcement Learning

ICML 2025arXiv

citations

Adaptive Accompaniment with ReaLchords

ICML 2024arXiv

citations

Pablo Samuel Castro

papers (16)

Deep Reinforcement Learning at the Edge of the Statistical Precipice

Minigrid & Miniworld: Modular & Customizable Reinforcement Learning Environments for Goal-Oriented Tasks

Stop Regressing: Training Value Functions via Classification for Scalable Deep RL

Reincarnating Reinforcement Learning: Reusing Prior Computation to Accelerate Progress

The Difficulty of Passive Learning in Deep Reinforcement Learning

Mixtures of Experts Unlock Parameter Scaling for Deep RL

MICo: Improved representations via sampling-based state similarity for Markov decision processes

In value-based deep reinforcement learning, a pruned network is a good network

Small batch deep reinforcement learning

Stable Gradients for Stable Learning at Scale in Deep Reinforcement Learning

The Impact of On-Policy Parallelized Data Collection on Deep Reinforcement Learning Networks

Mitigating Plasticity Loss in Continual Reinforcement Learning by Reducing Churn

Studying the Interplay Between the Actor and Critic Representations in Reinforcement Learning

Measure gradients, not activations! Enhancing neuronal activity in deep reinforcement learning

The Courage to Stop: Overcoming Sunk Cost Fallacy in Deep Reinforcement Learning

Adaptive Accompaniment with ReaLchords

papers (16)

Deep Reinforcement Learning at the Edge of the Statistical Precipice

Minigrid & Miniworld: Modular & Customizable Reinforcement Learning Environments for Goal-Oriented Tasks

Stop Regressing: Training Value Functions via Classification for Scalable Deep RL

Reincarnating Reinforcement Learning: Reusing Prior Computation to Accelerate Progress

The Difficulty of Passive Learning in Deep Reinforcement Learning

Mixtures of Experts Unlock Parameter Scaling for Deep RL

MICo: Improved representations via sampling-based state similarity for Markov decision processes

In value-based deep reinforcement learning, a pruned network is a good network

Small batch deep reinforcement learning

Stable Gradients for Stable Learning at Scale in Deep Reinforcement Learning

The Impact of On-Policy Parallelized Data Collection on Deep Reinforcement Learning Networks

Mitigating Plasticity Loss in Continual Reinforcement Learning by Reducing Churn

Studying the Interplay Between the Actor and Critic Representations in Reinforcement Learning

Measure gradients, not activations! Enhancing neuronal activity in deep reinforcement learning

The Courage to Stop: Overcoming Sunk Cost Fallacy in Deep Reinforcement Learning

Adaptive Accompaniment with ReaLchords