Curated cross-environment GradLab research releases.
🔄 In a Training Loop
Tiago Silva
tsilva
AI & ML interests
Deep Reinforcement Learning
Recent Activity
updated a dataset 1 day ago
tsilva/gradlab-breakout-trajectories published a dataset 2 days ago
tsilva/gradlab-breakout-trajectories updated a dataset about 1 month ago
tsilva/supermariobros-nes-turbo-benchmarksOrganizations
Legacy rlab / Stable-Baselines3 PPO research releases for SuperMarioBros-Nes-v0.
-
tsilva/Level1-1_stable-baselines3-ppo_7d9b9131
Reinforcement Learning • Updated • 13 -
tsilva/Level1-2_stable-baselines3-ppo_91df110f
Reinforcement Learning • Updated • 20 -
tsilva/Level1-4_stable-baselines3-ppo_be9abbc8
Reinforcement Learning • Updated • 13 -
tsilva/Level2-1_stable-baselines3-ppo_4792f358
Reinforcement Learning • Updated • 13
Curated cross-environment GradLab research releases.
Evidence-backed GradLab research releases for VizdoomDeathmatch-v1.
Legacy rlab / Stable-Baselines3 PPO research releases for SuperMarioBros-Nes-v0.
-
tsilva/Level1-1_stable-baselines3-ppo_7d9b9131
Reinforcement Learning • Updated • 13 -
tsilva/Level1-2_stable-baselines3-ppo_91df110f
Reinforcement Learning • Updated • 20 -
tsilva/Level1-4_stable-baselines3-ppo_be9abbc8
Reinforcement Learning • Updated • 13 -
tsilva/Level2-1_stable-baselines3-ppo_4792f358
Reinforcement Learning • Updated • 13
MNIST classification using different recipes.