524339208's workspace
Runs
1,554
Name
17 visualized
algo: PPOLag
algo: PPOLag
2
algo: PCPO
algo: PCPO
3
algo: CUP
algo: CUP
4
algo: CPO
algo: CPO
5
algo: FOCOPS
algo: FOCOPS
3
State
Notes
User
Tags
Created
Runtime
Sweep
algo
algo_cfgs.adv_estimation_method
algo_cfgs.batch_size
algo_cfgs.cg_damping
algo_cfgs.cg_iters
algo_cfgs.clip
algo_cfgs.cost_gamma
algo_cfgs.cost_normalize
algo_cfgs.critic_norm_coef
algo_cfgs.entropy_coef
algo_cfgs.focops_eta
algo_cfgs.focops_lam
algo_cfgs.fvp_obs
algo_cfgs.fvp_sample_freq
algo_cfgs.gamma
algo_cfgs.kl_early_stop
algo_cfgs.lam
algo_cfgs.lam_c
algo_cfgs.max_grad_norm
algo_cfgs.obs_normalize
algo_cfgs.penalty_coef
algo_cfgs.reward_normalize
algo_cfgs.standardized_cost_adv
algo_cfgs.standardized_rew_adv
algo_cfgs.steps_per_epoch
algo_cfgs.target_kl
algo_cfgs.update_cycle
algo_cfgs.update_iters
algo_cfgs.use_cost
algo_cfgs.use_critic_norm
algo_cfgs.use_max_grad_norm
env_id
exp_increment_cfgs.algo_cfgs.cost_normalize
exp_increment_cfgs.algo_cfgs.obs_normalize
exp_increment_cfgs.algo_cfgs.reward_normalize
exp_increment_cfgs.algo_cfgs.steps_per_epoch
exp_increment_cfgs.algo_cfgs.update_cycle
exp_increment_cfgs.logger_cfgs.log_dir
exp_increment_cfgs.logger_cfgs.use_wandb
exp_increment_cfgs.seed
exp_increment_cfgs.train_cfgs.torch_threads
exp_increment_cfgs.train_cfgs.total_steps
exp_increment_cfgs.train_cfgs.vector_env_nums
exp_name
Finished
524339208
7m 9s
-
PPOLag
gae
64
-
-
0.2
0.99
false
0.001
0
-
-
-
-
0.99
true
0.95
0.95
40
true
0
false
true
true
-
0.02
20000
40
true
true
true
SafetyPointGoal1-v0
false
true
false
-
20000
./exp-x/sg_benchmark_1e7_paper/SafetyPointGoal1-v0---2a03030fa246cc234fe9093b3484bf3e1d69eee9367e723cca38d98b6f80c5d5/
false
10
1
10000000
20
PPOLag-{SafetyPointGoal1-v0}
Finished
524339208
1m 12s
-
PCPO
gae
128
0.1
15
-
0.99
false
0.001
0
-
-
None
1
0.99
false
0.95
0.95
40
true
0
false
true
true
20000
0.01
-
10
true
true
true
SafetyPointGoal1-v0
-
-
-
20000
-
./exp-x/Goal_seed_6_3/SafetyPointGoal1-v0---ce52d81b85f48e19e44caa0a9cdae56671981be7b3e6f30dc970b0f8908df7d5/
false
21.66667
2
10000000
10
PCPO-{SafetyPointGoal1-v0}
Finished
524339208
3m 12s
-
CUP
gae
64
-
-
0.2
0.99
false
0.001
0
-
-
-
-
0.99
true
0.95
0.95
40
true
0
false
true
true
-
0.01
20000
40
true
true
true
SafetyPointGoal1-v0
false
true
false
-
20000
./exp-x/sg_benchmark_1e7_paper/SafetyPointGoal1-v0---15fbabecb55517e6a4545480f541c8940ddeb2b4f7d89cbbe0801ca1c4c74d1d/
false
10
1
10000000
20
CUP-{SafetyPointGoal1-v0}
Finished
524339208
15m 35s
-
CPO
gae
128
0.1
15
-
0.99
false
0.001
0
-
-
None
1
0.99
false
0.95
0.95
40
true
0
false
true
true
20000
0.01
-
10
true
true
true
SafetyPointGoal1-v0
-
-
-
20000
-
./exp-x/Goal_seed_6_3/SafetyPointGoal1-v0---62594028668f3f9a50cd26599f9770f12e9708b963c868a8c126a2797be8a0f2/
false
22
2
10000000
10
CPO-{SafetyPointGoal1-v0}
Finished
524339208
5m 40s
-
FOCOPS
gae
64
-
-
0.2
0.99
false
0.001
0
0.02
1.5
-
-
0.99
true
0.95
0.95
40
true
0
false
true
true
-
0.02
20000
40
true
true
true
SafetyPointGoal1-v0
false
true
false
-
20000
./exp-x/sg_benchmark_1e7_paper/SafetyPointGoal1-v0---e7103fbfb55ef408eedc879761fdc80b0deee36b98597fa8e1a7a163696a70b4/
false
10
1
10000000
20
FOCOPS-{SafetyPointGoal1-v0}
1-5
of 5