nickhe/TTRL_gameagent_Frostbite_10epochs
Updated
Zhiyuan He
nickhe
·
AI & ML interests
None yet
Recent Activity
published a model 3 months ago
nickhe/firl-ckpt-720 published a model 3 months ago
nickhe/firl-ckpt-760Organizations
nickhe/TTRL_gameagent_Freeway_10epochs
Updated
nickhe/TTRL_gameagent_CrazyClimber_10epochs
Updated
nickhe/TTRL_gameagent_Berzerk_10epochs
Updated
nickhe/rl_dqn_all_lora_kl_0915-step_4800
Updated
nickhe/rl_dqn_all_lora_kl_0915-step_4500
Updated
nickhe/rl_dqn_all_lora_kl_0915-step_4200
Updated
nickhe/rl_dqn_all_lora_kl_0915-step_3900
Updated
nickhe/rl_dqn_all_lora_kl_0915-step_2700
Updated
nickhe/rl_dqn_all_lora_kl_0915-step_1800
Updated
nickhe/rl_dqn_all_lora_kl_0915-step_1600
Updated
nickhe/dr_verl_4gpu_0920_math7b_step_1200
8B • Updated • 2
nickhe/dr_verl_4gpu_0920_math7b_step_900
8B • Updated
nickhe/dr_verl_4gpu_0920_math7b_step_600
Updated
nickhe/dr_verl_4gpu_0920_math7b_step_300
8B • Updated
nickhe/dqn_lora_TT_rl_ckpt4000_0918_step_1600
Updated
nickhe/dqn_lora_TT_rl_ckpt4000_0918_step_1400
Updated
nickhe/dqn_lora_TT_rl_ckpt4000_0918_step_1000
Updated
nickhe/dqn_lora_TT_rl_ckpt4000_0918_step_800
Updated
nickhe/rl_dqn_all_lora_kl_0915_step_1200
Updated
nickhe/rl_env_all_lora_0827
Updated
nickhe/ga_rl_sports_15_AUG
Updated
nickhe/dr-verl-0915-step300
8B • Updated
nickhe/dr-verl-0915-step600
8B • Updated
nickhe/atari_sft_maze-ckpt-2500
8B • Updated
nickhe/rl_env_shooting4f_lora_0827-ckpt-400
Updated
nickhe/rl_env_all_all_games_lora_0827-ckpt-600
Updated
nickhe/rl_env_all_all_games_lora_0827-ckpt-400
Updated
nickhe/rl_env_shooting4f_lora_0827-ckpt-200
Updated
nickhe/rl-lora-env-reward-ckpt-400
Updated