Tahsin Rahit

published a Space about 1 hour ago

Reproduction: Efficiently Learning Drifting Halfspaces with Massart Noise

published a bucket about 1 hour ago

rahit/repro-efficiently-learning-drifting-halfspaces-with-massart-noise-artifacts

0 Bytes

updated a bucket about 3 hours ago

rahit/sdgad-tmp-artifact-bucket-3

published a bucket about 3 hours ago

rahit/sdgad-tmp-artifact-bucket-3

updated a bucket about 3 hours ago

rahit/sdgad-tmp-artifact-bucket-2

published a bucket about 3 hours ago

rahit/sdgad-tmp-artifact-bucket-2

updated a bucket about 3 hours ago

rahit/sdgad-tmp-artifact-bucket

published a bucket about 3 hours ago

rahit/sdgad-tmp-artifact-bucket

updated a bucket about 3 hours ago

rahit/repro-gffmerge-efficient-merging-of-graph-neural-force-fields-and-beyond-artifacts

372 kB

updated a Space about 6 hours ago

Reproduction: Understanding Behavior Cloning with Action Quantization

Explore experiment logs and collaborate with an AI agent

published a Space about 6 hours ago

Reproduction: Understanding Behavior Cloning with Action Quantization

Explore experiment logs and collaborate with an AI agent

updated a bucket about 6 hours ago

rahit/repro-understanding-behavior-cloning-with-action-quantization-artifacts

published a bucket about 6 hours ago

rahit/repro-understanding-behavior-cloning-with-action-quantization-artifacts

updated a bucket about 6 hours ago

rahit/ubcaq-repro-bucket

published a bucket about 6 hours ago

rahit/ubcaq-repro-bucket

updated a Space about 7 hours ago

Reproduction: Why Linear Recurrent Memory Works in Partially Observable Reinforcement Learning

Explore research logbook and sync with AI agent

published a Space about 7 hours ago

Reproduction: Why Linear Recurrent Memory Works in Partially Observable Reinforcement Learning