Breakout datasets: HUD-masked collection, full-HUD Checkpoint Monitoring Runs, and derived world models.
🔄 In a Training Loop
Tiago Silva
tsilva
AI & ML interests
Deep Reinforcement Learning
Recent Activity
updated a model about 16 hours ago
tsilva/SuperMarioBros-Nes-v0_Level1-3 published a model about 16 hours ago
tsilva/SuperMarioBros-Nes-v0_Level1-3 updated a model about 1 month ago
tsilva/Level4-1_stable-baselines3-ppo_fe8a02dcOrganizations
models 33
tsilva/SuperMarioBros-Nes-v0_Level1-3
Reinforcement Learning • Updated • 17
tsilva/Level4-1_stable-baselines3-ppo_fe8a02dc
Reinforcement Learning • Updated • 10
tsilva/Level2-3_stable-baselines3-ppo_ff330a59
Reinforcement Learning • Updated • 3
tsilva/Level3-2_stable-baselines3-ppo_945d412a
Reinforcement Learning • Updated • 3
tsilva/Level3-3_stable-baselines3-ppo_d52f7c68
Reinforcement Learning • Updated • 6
tsilva/Level3-4_stable-baselines3-ppo_4141caab
Reinforcement Learning • Updated • 4
tsilva/Level1-2_stable-baselines3-ppo_91df110f
Reinforcement Learning • Updated • 15
tsilva/Level1-4_stable-baselines3-ppo_be9abbc8
Reinforcement Learning • Updated • 7
tsilva/Level2-1_stable-baselines3-ppo_4792f358
Reinforcement Learning • Updated • 8
tsilva/Level1-1_stable-baselines3-ppo_7d9b9131
Reinforcement Learning • Updated • 27
datasets 44
tsilva/gradlab-breakout-c6d579da
Viewer • Updated • 27.9M • 38
tsilva/gradlab-breakout-6127e81d
Viewer • Updated • 3.98M • 212
tsilva/gradlab-breakout-checkpoint-evals
Viewer • Updated • 400 • 332
tsilva/gradlab-breakout-trajectories
Viewer • Updated • 12.7M • 1.25k
tsilva/NES-SuperMarioBros_Level1-1_gray84-hudcrop-stack4-simple_ppo
Viewer • Updated • 498 • 34
tsilva/supermariobros-nes-turbo-benchmarks
Updated • 12
tsilva/gymrec__ALE_slash_Breakout_dash_v5
Updated • 4
tsilva/llmstyler-job-scripts
Updated • 1
tsilva/stylemix_trump-v3
Viewer • Updated • 2.16k • 7
tsilva/smoltalk_style_mix-v3
Viewer • Updated • 2.4k • 7