Authoranonymousaa's workspace
Runs
56
Name
56 visualized
State
Notes
User
Tags
Created
Runtime
Sweep
_target_
act_steps
action_dim
base_policy_path
cond_steps
denoising_steps
device
env.best_reward_threshold_for_success
env.max_episode_steps
env.n_envs
env.name
env.reset_at_iteration
env.save_video
env.wrappers.mujoco_locomotion_lowdim.normalization_path
env.wrappers.multi_step.max_episode_steps
env.wrappers.multi_step.n_action_steps
env.wrappers.multi_step.n_obs_steps
env.wrappers.multi_step.reset_within_step
env_name
ft_denoising_steps
horizon_steps
logdir
max_std
min_std
model._target_
model.act_dim
model.act_max
model.act_min
model.actor_policy_path
model.clip_ploss_coef
model.clip_ploss_coef_base
model.clip_ploss_coef_rate
model.cond_steps
model.critic._target_
model.critic.activation_type
model.critic.cond_dim
model.critic.mlp_dims
model.critic.residual_style
model.denoised_clip_value
model.device
model.explore_net_activation_type
model.ft_denoising_steps
model.horizon_steps
model.inference_steps
Finished
-
tonghezhang01
13h 4m 1s
-
agent.finetune.reinflow.train_ppo_flow_agent.TrainPPOFlowAgent
4
3
log_gym_d4rl/hopper-medium-v2/Shortcut/state_40.pt
1
4
cuda:2
3
1000
40
hopper-medium-v2
false
false
gym_d4rl_normalization/hopper-medium-v2/normalization.npz
1000
4
1
true
hopper-medium-v2
4
4
/home/yuchao/ReinFlow/log/gym/finetune/hopper-medium-v2_ppo_shortcut_mlp_ta4_td4_tdf4/2025-05-22_13-48-44_seed42
0.24
0.1
model.flow.ft_ppo.pposhortcut.PPOShortCut
3
1
-1
log_gym_d4rl/hopper-medium-v2/Shortcut/state_40.pt
0.01
0.01
3
1
model.common.critic.CriticObs
Mish
11
[256,256,256]
true
1
cuda:2
Tanh
4
4
4
Finished
-
tonghezhang01
9h 33m 30s
-
agent.finetune.reinflow.train_ppo_flow_agent.TrainPPOFlowAgent
4
3
log_gym_d4rl/hopper-medium-v2/Shortcut/state_40.pt
1
4
cuda:1
3
1000
40
hopper-medium-v2
false
false
gym_d4rl_normalization/hopper-medium-v2/normalization.npz
1000
4
1
true
hopper-medium-v2
4
4
/home/yuchao/ReinFlow/log/gym/finetune/hopper-medium-v2_ppo_shortcut_mlp_ta4_td4_tdf4/2025-05-22_13-48-44_seed0
0.24
0.1
model.flow.ft_ppo.pposhortcut.PPOShortCut
3
1
-1
log_gym_d4rl/hopper-medium-v2/Shortcut/state_40.pt
0.01
0.01
3
1
model.common.critic.CriticObs
Mish
11
[256,256,256]
true
1
cuda:1
Tanh
4
4
4
Finished
-
tonghezhang01
2h 29m 19s
-
agent.finetune.reinflow.train_ppo_flow_agent.TrainPPOFlowAgent
4
3
log_gym_d4rl/hopper-medium-v2/Shortcut/state_40.pt
1
4
cuda:0
3
1000
40
hopper-medium-v2
false
false
gym_d4rl_normalization/hopper-medium-v2/normalization.npz
1000
4
1
true
hopper-medium-v2
4
4
/home/yuchao/ReinFlow/log/gym/finetune/hopper-medium-v2_ppo_shortcut_mlp_ta4_td4_tdf4/2025-05-22_13-48-44_seed3407
0.24
0.1
model.flow.ft_ppo.pposhortcut.PPOShortCut
3
1
-1
log_gym_d4rl/hopper-medium-v2/Shortcut/state_40.pt
0.01
0.01
3
1
model.common.critic.CriticObs
Mish
11
[256,256,256]
true
1
cuda:0
Tanh
4
4
4
Finished
-
tonghezhang01
4h 9m 54s
-
agent.finetune.reinflow.train_ppo_flow_agent.TrainPPOFlowAgent
4
3
log_gym_d4rl/hopper-medium-v2/1-ReFlow/state_40.pt
1
4
cuda:5
3
1000
40
hopper-medium-v2
false
false
gym_d4rl_normalization/gym-d4rl-normalization/hopper-medium-v2/normalization.npz
1000
4
1
true
hopper-medium-v2
4
4
/home/zhangtonghe/dppo/log/gym/finetune/hopper-medium-v2_ppo_reflow_mlp_ta4_td4_tdf4/2025-05-22_11-40-48_seed3407
0.24
0.1
model.flow.ft_ppo.ppoflow.PPOFlow
3
1
-1
log_gym_d4rl/hopper-medium-v2/1-ReFlow/state_40.pt
0.01
0.01
3
1
model.common.critic.CriticObs
Mish
11
[256,256,256]
true
1
cuda:5
Tanh
4
4
4
Finished
-
tonghezhang01
3h 57m 56s
-
agent.finetune.reinflow.train_ppo_flow_agent.TrainPPOFlowAgent
4
3
log_gym_d4rl/hopper-medium-v2/1-ReFlow/state_40.pt
1
4
cuda:6
3
1000
40
hopper-medium-v2
false
false
gym_d4rl_normalization/gym-d4rl-normalization/hopper-medium-v2/normalization.npz
1000
4
1
true
hopper-medium-v2
4
4
/home/zhangtonghe/dppo/log/gym/finetune/hopper-medium-v2_ppo_reflow_mlp_ta4_td4_tdf4/2025-05-22_11-40-47_seed0
0.24
0.1
model.flow.ft_ppo.ppoflow.PPOFlow
3
1
-1
log_gym_d4rl/hopper-medium-v2/1-ReFlow/state_40.pt
0.01
0.01
3
1
model.common.critic.CriticObs
Mish
11
[256,256,256]
true
1
cuda:6
Tanh
4
4
4
Finished
-
tonghezhang01
1d 2h 4m 11s
-
agent.finetune.reinflow.train_ppo_diffusion_agent.TrainPPODiffusionAgent
4
3
log_gym_d4rl/hopper-medium-v2/DDPM/state_120.pt
1
20
cuda:3
3
1000
40
hopper-medium-v2
false
false
gym_d4rl_normalization/gym-d4rl-normalization/hopper-medium-v2/normalization.npz
1000
4
1
true
hopper-medium-v2
10
4
/home/zhangtonghe/dppo/log/gym/finetune/hopper-medium-v2_ppo_diffusion_mlp_ta4_td4_d4rl_seed0/2025-05-22_11-40-47_0
-
-
model.diffusion.diffusion_ppo.PPODiffusion
-
-
-
-
0.01
0.01
3
-
model.common.critic.CriticObs
Mish
11
[256,256,256]
true
-
cuda:3
-
10
4
-
Finished
-
tonghezhang01
8h 27m 42s
-
agent.finetune.reinflow.train_ppo_flow_agent.TrainPPOFlowAgent
4
3
log_gym_d4rl/hopper-medium-v2/1-ReFlow/state_40.pt
1
4
cuda:7
3
1000
40
hopper-medium-v2
false
false
gym_d4rl_normalization/gym-d4rl-normalization/hopper-medium-v2/normalization.npz
1000
4
1
true
hopper-medium-v2
4
4
/home/zhangtonghe/dppo/log/gym/finetune/hopper-medium-v2_ppo_reflow_mlp_ta4_td4_tdf4/2025-05-22_11-40-46_seed42
0.24
0.1
model.flow.ft_ppo.ppoflow.PPOFlow
3
1
-1
log_gym_d4rl/hopper-medium-v2/1-ReFlow/state_40.pt
0.01
0.01
3
1
model.common.critic.CriticObs
Mish
11
[256,256,256]
true
1
cuda:7
Tanh
4
4
4
Finished
-
tonghezhang01
1d 2h 10m 15s
-
agent.finetune.reinflow.train_ppo_diffusion_agent.TrainPPODiffusionAgent
4
3
log_gym_d4rl/hopper-medium-v2/DDPM/state_120.pt
1
20
cuda:2
3
1000
40
hopper-medium-v2
false
false
gym_d4rl_normalization/gym-d4rl-normalization/hopper-medium-v2/normalization.npz
1000
4
1
true
hopper-medium-v2
10
4
/home/zhangtonghe/dppo/log/gym/finetune/hopper-medium-v2_ppo_diffusion_mlp_ta4_td4_d4rl_seed3407/2025-05-22_11-40-46_3407
-
-
model.diffusion.diffusion_ppo.PPODiffusion
-
-
-
-
0.01
0.01
3
-
model.common.critic.CriticObs
Mish
11
[256,256,256]
true
-
cuda:2
-
10
4
-
Finished
-
tonghezhang01
1d 1h 53m 39s
-
agent.finetune.reinflow.train_ppo_diffusion_agent.TrainPPODiffusionAgent
4
3
log_gym_d4rl/hopper-medium-v2/DDPM/state_120.pt
1
20
cuda:4
3
1000
40
hopper-medium-v2
false
false
gym_d4rl_normalization/gym-d4rl-normalization/hopper-medium-v2/normalization.npz
1000
4
1
true
hopper-medium-v2
10
4
/home/zhangtonghe/dppo/log/gym/finetune/hopper-medium-v2_ppo_diffusion_mlp_ta4_td4_d4rl_seed42/2025-05-22_11-40-47_42
-
-
model.diffusion.diffusion_ppo.PPODiffusion
-
-
-
-
0.01
0.01
3
-
model.common.critic.CriticObs
Mish
11
[256,256,256]
true
-
cuda:4
-
10
4
-
Finished
-
tonghezhang01
1d 14h 59m 55s
-
agent.finetune.flow_baselines.train_fql_agent.TrainFQLAgent
4
3
-
1
4
cuda:0
3
1000
1
hopper-medium-v2
false
false
/home/zhangtonghe/ReinFlow/data-offline/gym/hopper-medium-v2/normalization.npz
1000
4
1
true
hopper-medium-v2
-
4
/home/zhangtonghe/ReinFlow/log/gym/finetune/hopper-medium-v2_fql_mlp_ta4_td4_seed0/2025-05-10_13-16-06_0
-
-
model.flow.ft_baselines.fql.FQLModel
-
-
-
-
-
-
-
-
model.common.critic.CriticObsAct
ReLU
11
[256,256]
-
-
cuda:0
-
-
-
4
Finished
-
tonghezhang01
1d 14h 59m 41s
-
agent.finetune.flow_baselines.train_fql_agent.TrainFQLAgent
4
3
-
1
4
cuda:0
3
1000
1
hopper-medium-v2
false
false
/home/zhangtonghe/ReinFlow/data-offline/gym/hopper-medium-v2/normalization.npz
1000
4
1
true
hopper-medium-v2
-
4
/home/zhangtonghe/ReinFlow/log/gym/finetune/hopper-medium-v2_fql_mlp_ta4_td4_seed3407/2025-05-10_13-16-06_3407
-
-
model.flow.ft_baselines.fql.FQLModel
-
-
-
-
-
-
-
-
model.common.critic.CriticObsAct
ReLU
11
[256,256]
-
-
cuda:0
-
-
-
4
Finished
-
tonghezhang01
8h 56m 41s
-
agent.finetune.flow_baselines.train_fql_agent.TrainFQLAgent
4
3
-
1
4
cuda:0
3
1000
1
hopper-medium-v2
false
false
/home/zhangtonghe/ReinFlow/data-offline/gym/hopper-medium-v2/normalization.npz
1000
4
1
true
hopper-medium-v2
-
4
/home/zhangtonghe/ReinFlow/log/gym/finetune/hopper-medium-v2_fql_mlp_ta4_td4/2025-05-09_11-54-21_42
-
-
model.flow.ft_baselines.fql.FQLModel
-
-
-
-
-
-
-
-
model.common.critic.CriticObsAct
ReLU
11
[256,256]
-
-
cuda:0
-
-
-
4
Finished
-
tonghezhang01
46s
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
Killed
-
tonghezhang01
1m 29s
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
Finished
-
tonghezhang01
28s
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
Finished
-
tonghezhang01
9h 16m 1s
-
agent.finetune.mine.train_ppo_flow_agent.TrainPPOFlowAgent
4
3
/home/zhangtonghe/ReinFlow/log/gym/pretrain/hopper-v2/ReFlow/2025-02-06_01-35-03_42_state_1500.pt
1
4
cuda:2
3
1000
40
hopper-medium-v2
false
false
/home/zhangtonghe/ReinFlow/data/gym/hopper-medium-v2/normalization.npz
1000
4
1
true
hopper-medium-v2
4
4
/home/zhangtonghe/ReinFlow/log/gym/finetune/hopper-medium-v2_ppo_reflow_mlp_ta4_td4_tdf4/2025-04-28_21-53-42_seed3407
0.24
0.1
model.flow.ft_ppo.ppoflow.PPOFlow
3
1
-1
/home/zhangtonghe/ReinFlow/log/gym/pretrain/hopper-v2/ReFlow/2025-02-06_01-35-03_42_state_1500.pt
0.01
0.01
3
1
model.common.critic.CriticObs
Mish
11
[256,256,256]
true
1
cuda:2
Tanh
4
4
4
Finished
-
tonghezhang01
9h 21m 30s
-
agent.finetune.mine.train_ppo_flow_agent.TrainPPOFlowAgent
4
3
/home/zhangtonghe/ReinFlow/log/gym/pretrain/hopper-v2/ReFlow/2025-02-06_01-35-03_42_state_1500.pt
1
4
cuda:1
3
1000
40
hopper-medium-v2
false
false
/home/zhangtonghe/ReinFlow/data/gym/hopper-medium-v2/normalization.npz
1000
4
1
true
hopper-medium-v2
4
4
/home/zhangtonghe/ReinFlow/log/gym/finetune/hopper-medium-v2_ppo_reflow_mlp_ta4_td4_tdf4/2025-04-28_21-53-30_seed42
0.24
0.1
model.flow.ft_ppo.ppoflow.PPOFlow
3
1
-1
/home/zhangtonghe/ReinFlow/log/gym/pretrain/hopper-v2/ReFlow/2025-02-06_01-35-03_42_state_1500.pt
0.01
0.01
3
1
model.common.critic.CriticObs
Mish
11
[256,256,256]
true
1
cuda:1
Tanh
4
4
4
Finished
-
tonghezhang01
7h 46m 15s
-
agent.finetune.mine.train_ppo_flow_agent.TrainPPOFlowAgent
4
3
/home/zhangtonghe/ReinFlow/log/gym/pretrain/hopper-v2/ReFlow/2025-02-06_01-35-03_42_state_1500.pt
1
4
cuda:0
3
1000
40
hopper-medium-v2
false
false
/home/zhangtonghe/ReinFlow/data/gym/hopper-medium-v2/normalization.npz
1000
4
1
true
hopper-medium-v2
4
4
/home/zhangtonghe/ReinFlow/log/gym/finetune/hopper-medium-v2_ppo_reflow_mlp_ta4_td4_tdf4/2025-04-28_21-52-13_seed0
0.24
0.1
model.flow.ft_ppo.ppoflow.PPOFlow
3
1
-1
/home/zhangtonghe/ReinFlow/log/gym/pretrain/hopper-v2/ReFlow/2025-02-06_01-35-03_42_state_1500.pt
0.01
0.01
3
1
model.common.critic.CriticObs
Mish
11
[256,256,256]
true
1
cuda:0
Tanh
4
4
4
Finished
-
destiny0621
32m 20s
-
agent.finetune.train_ppo_gaussian_agent.TrainPPOGaussianAgent
1
3
-
1
-
cuda:3
3
1000
10
hopper-medium-v2
false
false
/home/susichang/dppo/data/gym/hopper-medium-v2/normalization.npz
1000
1
1
true
hopper-medium-v2
-
1
/home/susichang/dppo/log/gym-finetune/hopper-medium-v2_nopre_ppo_gaussian_mlp_ta1/2025-04-26_15-18-42_3407
-
-
model.rl.gaussian_ppo.PPO_Gaussian
-
-
-
-
0.1
-
-
-
model.common.critic.CriticObs
Mish
11
[256,256,256]
true
-
cuda:3
-
-
1
-
Finished
-
destiny0621
31m 7s
-
agent.finetune.train_ppo_gaussian_agent.TrainPPOGaussianAgent
1
3
-
1
-
cuda:2
3
1000
10
hopper-medium-v2
false
false
/home/susichang/dppo/data/gym/hopper-medium-v2/normalization.npz
1000
1
1
true
hopper-medium-v2
-
1
/home/susichang/dppo/log/gym-finetune/hopper-medium-v2_nopre_ppo_gaussian_mlp_ta1/2025-04-26_15-14-54_0
-
-
model.rl.gaussian_ppo.PPO_Gaussian
-
-
-
-
0.1
-
-
-
model.common.critic.CriticObs
Mish
11
[256,256,256]
true
-
cuda:2
-
-
1
-
1-20
of 56