Zhiyuan He

nickhe 's models 69

Sort:  Recently updated

nickhe/TTRL_gameagent_Frostbite_10epochs

Updated Oct 16, 2025

nickhe/TTRL_gameagent_Freeway_10epochs

Updated Oct 16, 2025

nickhe/TTRL_gameagent_CrazyClimber_10epochs

Updated Oct 16, 2025

nickhe/TTRL_gameagent_Berzerk_10epochs

Updated Oct 16, 2025

nickhe/rl_dqn_all_lora_kl_0915-step_4800

Updated Oct 13, 2025

nickhe/rl_dqn_all_lora_kl_0915-step_4500

Updated Oct 13, 2025

nickhe/rl_dqn_all_lora_kl_0915-step_4200

Updated Oct 13, 2025

nickhe/rl_dqn_all_lora_kl_0915-step_3900

Updated Oct 13, 2025

nickhe/rl_dqn_all_lora_kl_0915-step_2700

Updated Oct 13, 2025

nickhe/rl_dqn_all_lora_kl_0915-step_1800

Updated Oct 13, 2025

nickhe/rl_dqn_all_lora_kl_0915-step_1600

Updated Oct 5, 2025

nickhe/dr_verl_4gpu_0920_math7b_step_1200

8B • Updated Sep 24, 2025 • 3

nickhe/dr_verl_4gpu_0920_math7b_step_900

8B • Updated Sep 24, 2025 • 3

nickhe/dr_verl_4gpu_0920_math7b_step_600

Updated Sep 24, 2025

nickhe/dr_verl_4gpu_0920_math7b_step_300

8B • Updated Sep 23, 2025 • 2

nickhe/dqn_lora_TT_rl_ckpt4000_0918_step_1600

Updated Sep 23, 2025

nickhe/dqn_lora_TT_rl_ckpt4000_0918_step_1400

Updated Sep 23, 2025

nickhe/dqn_lora_TT_rl_ckpt4000_0918_step_1000

Updated Sep 23, 2025

nickhe/dqn_lora_TT_rl_ckpt4000_0918_step_800

Updated Sep 23, 2025

nickhe/rl_dqn_all_lora_kl_0915_step_1200

Updated Sep 19, 2025

nickhe/rl_env_all_lora_0827

Updated Sep 17, 2025

nickhe/ga_rl_sports_15_AUG

Updated Sep 17, 2025

nickhe/dr-verl-0915-step300

8B • Updated Sep 16, 2025 • 5

nickhe/dr-verl-0915-step600

8B • Updated Sep 16, 2025 • 4

nickhe/atari_sft_maze-ckpt-2500

8B • Updated Sep 4, 2025 • 2

nickhe/rl_env_shooting4f_lora_0827-ckpt-400

Updated Sep 1, 2025

nickhe/rl_env_all_all_games_lora_0827-ckpt-600

Updated Sep 1, 2025

nickhe/rl_env_all_all_games_lora_0827-ckpt-400

Updated Aug 31, 2025

nickhe/rl_env_shooting4f_lora_0827-ckpt-200

Updated Aug 31, 2025

nickhe/rl-lora-env-reward-ckpt-400

Updated Aug 30, 2025