Tiago Silva

tsilva's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

updated 9 models about 9 hours ago

tsilva/Level4-1_stable-baselines3-ppo_fe8a02dc

Reinforcement Learning • Updated about 9 hours ago • 3

tsilva/Level3-4_stable-baselines3-ppo_4141caab

Reinforcement Learning • Updated about 9 hours ago • 8

tsilva/Level3-3_stable-baselines3-ppo_d52f7c68

Reinforcement Learning • Updated about 9 hours ago • 11

tsilva/Level3-2_stable-baselines3-ppo_945d412a

Reinforcement Learning • Updated about 9 hours ago • 3

tsilva/Level2-3_stable-baselines3-ppo_ff330a59

Reinforcement Learning • Updated about 9 hours ago • 12

tsilva/Level2-1_stable-baselines3-ppo_4792f358

Reinforcement Learning • Updated about 9 hours ago • 7

tsilva/Level1-4_stable-baselines3-ppo_be9abbc8

Reinforcement Learning • Updated about 9 hours ago • 4

tsilva/Level1-2_stable-baselines3-ppo_91df110f

Reinforcement Learning • Updated about 9 hours ago • 11

tsilva/Level1-1_stable-baselines3-ppo_7d9b9131

Reinforcement Learning • Updated about 9 hours ago • 10

updated 2 collections 8 days ago

GradLab — SuperMarioBros-Nes-v0

Collection

Historical rlab / Stable-Baselines3 PPO Policies, plus a separate gymrec recording. These are not GradLab-trained Checkpoints. • 10 items • Updated 8 days ago

GradLab — Breakout-Atari2600-v0

Collection

Breakout datasets: HUD-masked collection, full-HUD Checkpoint Monitoring Runs, and derived world models. • 6 items • Updated 8 days ago

updated 4 datasets 8 days ago

tsilva/NES-SuperMarioBros_Level1-1_gray84-hudcrop-stack4-simple_ppo

Viewer • Updated 8 days ago • 498 • 53

tsilva/gradlab-breakout-c6d579da

Viewer • Updated 8 days ago • 27.9M • 172

tsilva/gradlab-breakout-6127e81d

Viewer • Updated 8 days ago • 3.98M • 184

tsilva/gradlab-breakout-checkpoint-evals

Viewer • Updated 8 days ago • 400 • 189