Robot Learning Project

Cailyn Smith, Haoran Hao, Abien Cherian

Random Agent

random_agent_sideview.mp4

random_agent_frontview.mp4

On-Policy Agent (PPO)

Off-Policy Agent (SAC)

Model-based Agent (MBPO)

frontview_rollout_1.mp4

sideview_rollout_1.mp4

Modification 1 PPO-vision

eval_ep1_frontview.mp4

eval_ep1_sideview.mp4

Modification 2 Warmstart with Imitation Learning

Modification 3 Diffusion Policy with PPO expert

eval_ep1_frontview.gif

eval_ep1_sideview.gif

Performance

Page updated

Report abuse