Picture for Pablo Samuel Castro

Pablo Samuel Castro

Stable Gradients for Stable Learning at Scale in Deep Reinforcement Learning

Add code
Jun 18, 2025
Viaarxiv icon

Adaptive Accompaniment with ReaLchords

Add code
Jun 17, 2025
Viaarxiv icon

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

Add code
Jun 16, 2025
Viaarxiv icon

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

Add code
May 29, 2025
Viaarxiv icon

Mind the GAP! The Challenges of Scale in Pixel-based Deep Reinforcement Learning

Add code
May 23, 2025
Viaarxiv icon

Meta-World+: An Improved, Standardized, RL Benchmark

Add code
May 16, 2025
Viaarxiv icon

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

Add code
Mar 08, 2025
Viaarxiv icon

Multi-Task Reinforcement Learning Enables Parameter Scaling

Add code
Mar 07, 2025
Viaarxiv icon

CALE: Continuous Arcade Learning Environment

Add code
Oct 31, 2024
Viaarxiv icon

Don't flatten, tokenize! Unlocking the key to SoftMoE's efficacy in deep RL

Add code
Oct 02, 2024
Figure 1 for Don't flatten, tokenize! Unlocking the key to SoftMoE's efficacy in deep RL
Figure 2 for Don't flatten, tokenize! Unlocking the key to SoftMoE's efficacy in deep RL
Figure 3 for Don't flatten, tokenize! Unlocking the key to SoftMoE's efficacy in deep RL
Figure 4 for Don't flatten, tokenize! Unlocking the key to SoftMoE's efficacy in deep RL
Viaarxiv icon