Costa-huang's workspace
Runs
270
Name
30 visualized
State
Notes
User
Tags
Created
Runtime
Sweep
adaptation
anneal_lr
batch_size
capture_video
clip_coef
clip_vloss
cuda
end_a
end_e
ent_coef
exp_name
exploration_fraction
gae
gae_lambda
gamma
gym_id
kle_rollback
kle_stop
learning_rate
max_grad_norm
minibatch_size
n_minibatch
norm_adv
num_envs
num_steps
positive_likelihood
prod_mode
seed
shift
start_a
start_e
target_kl
torch_deterministic
total_timesteps
update_epochs
vf_coef
wandb_project_name
charts/episode_reward
charts/episode_reward/AttackRewardFunction
charts/episode_reward/CloserToEnemyBaseRewardFunction
charts/episode_reward/ProduceBuildingRewardFunction
charts/episode_reward/ProduceCombatUnitRewardFunction
charts/episode_reward/ProduceWorkerRewardFunction
charts/episode_reward/ResourceGatherRewardFunction
Finished
-
anonymous-rl-code
4h 13m 45s
-
2000000
true
1024
true
0.1
true
true
0.8
0.5
0.01
ppo_ac_positive_reward
0.8
true
0.95
0.99
MicrortsProduceCombatUnitHRL-v1
false
false
0.00025
0.5
256
4
true
8
128
1
true
3
2000000
1
1
0.03
true
10000000
4
0.5
action-guidance
10
0
7.70483
1
10
0
40
Finished
-
anonymous-rl-code
4h 39m 36s
-
2000000
true
1024
true
0.1
true
true
0.8
0.5
0.01
ppo_ac_positive_reward
0.8
true
0.95
0.99
MicrortsRandomEnemyHRL3-v1
false
false
0.00025
0.5
256
4
true
8
128
1
true
9
2000000
1
1
0.03
true
10000000
4
0.5
action-guidance
-1
14
8.21954
0
0
3
2
Finished
-
anonymous-rl-code
4h 57m 18s
-
2000000
true
1024
true
0.1
true
true
0.8
0.5
0.01
ppo_ac_positive_reward
0.8
true
0.95
0.99
MicrortsRandomEnemyHRL3-v1
false
false
0.00025
0.5
256
4
true
8
128
1
true
6
2000000
1
1
0.03
true
10000000
4
0.5
action-guidance
0
0
4.83365
0
0
5
1
Finished
-
anonymous-rl-code
4h 36m 51s
-
2000000
true
1024
true
0.1
true
true
0.8
0.5
0.01
ppo_ac_positive_reward
0.8
true
0.95
0.99
MicrortsRandomEnemyHRL3-v1
false
false
0.00025
0.5
256
4
true
8
128
1
true
7
2000000
1
1
0.03
true
10000000
4
0.5
action-guidance
1
16
7.81025
0
0
3
1
Finished
-
anonymous-rl-code
4h 42m 44s
-
2000000
true
1024
true
0.1
true
true
0.8
0.5
0.01
ppo_ac_positive_reward
0.8
true
0.95
0.99
MicrortsRandomEnemyHRL3-v1
false
false
0.00025
0.5
256
4
true
8
128
1
true
10
2000000
1
1
0.03
true
10000000
4
0.5
action-guidance
1
16
13.6205
0
0
3
0
Finished
-
anonymous-rl-code
4h 45m 23s
-
2000000
true
1024
true
0.1
true
true
0.8
0.5
0.01
ppo_ac_positive_reward
0.8
true
0.95
0.99
MicrortsRandomEnemyHRL3-v1
false
false
0.00025
0.5
256
4
true
8
128
1
true
8
2000000
1
1
0.03
true
10000000
4
0.5
action-guidance
1
15
7.81025
0
0
2
0
Finished
-
anonymous-rl-code
5h 14m 38s
-
2000000
true
1024
true
0.1
true
true
0.8
0.5
0.01
ppo_ac_positive_reward
0.8
true
0.95
0.99
MicrortsRandomEnemyHRL3-v1
false
false
0.00025
0.5
256
4
true
8
128
1
true
5
2000000
1
1
0.03
true
10000000
4
0.5
action-guidance
0
0
2.2375
2
5
2
34
Finished
-
anonymous-rl-code
4h 47m 59s
-
2000000
true
1024
true
0.1
true
true
0.8
0.5
0.01
ppo_ac_positive_reward
0.8
true
0.95
0.99
MicrortsRandomEnemyHRL3-v1
false
false
0.00025
0.5
256
4
true
8
128
1
true
4
2000000
1
1
0.03
true
10000000
4
0.5
action-guidance
0
14
19.01653
0
0
5
2
Finished
-
anonymous-rl-code
4h 59m 21s
-
2000000
true
1024
true
0.1
true
true
0.8
0.5
0.01
ppo_ac_positive_reward
0.8
true
0.95
0.99
MicrortsRandomEnemyHRL3-v1
false
false
0.00025
0.5
256
4
true
8
128
1
true
3
2000000
1
1
0.03
true
10000000
4
0.5
action-guidance
0
18
23.59072
0
0
5
0
Finished
-
anonymous-rl-code
5h 19m 28s
-
2000000
true
1024
true
0.1
true
true
0.8
0.5
0.01
ppo_ac_positive_reward
0.8
true
0.95
0.99
MicrortsProduceCombatUnitHRL-v1
false
false
0.00025
0.5
256
4
true
8
128
1
true
8
2000000
1
1
0.03
true
10000000
4
0.5
action-guidance
9
0
7.70483
1
9
0
40
Finished
-
anonymous-rl-code
5h 39m 17s
-
2000000
true
1024
true
0.1
true
true
0.8
0.5
0.01
ppo_ac_positive_reward
0.8
true
0.95
0.99
MicrortsProduceCombatUnitHRL-v1
false
false
0.00025
0.5
256
4
true
8
128
1
true
4
2000000
1
1
0.03
true
10000000
4
0.5
action-guidance
10
0
6.80533
1
10
0
40
Finished
-
anonymous-rl-code
5h 36m 16s
-
2000000
true
1024
true
0.1
true
true
0.8
0.5
0.01
ppo_ac_positive_reward
0.8
true
0.95
0.99
MicrortsProduceCombatUnitHRL-v1
false
false
0.00025
0.5
256
4
true
8
128
1
true
7
2000000
1
1
0.03
true
10000000
4
0.5
action-guidance
10
0
7.70483
1
10
0
40
Finished
-
anonymous-rl-code
4h 44m 40s
-
2000000
true
1024
true
0.1
true
true
0.8
0.5
0.01
ppo_ac_positive_reward
0.8
true
0.95
0.99
MicrortsRandomEnemyHRL3-v1
false
false
0.00025
0.5
256
4
true
8
128
1
true
2
2000000
1
1
0.03
true
10000000
4
0.5
action-guidance
1
15
7.81025
0
0
2
0
Finished
-
anonymous-rl-code
5h 15m 30s
-
2000000
true
1024
true
0.1
true
true
0.8
0.5
0.01
ppo_ac_positive_reward
0.8
true
0.95
0.99
MicrortsProduceCombatUnitHRL-v1
false
false
0.00025
0.5
256
4
true
8
128
1
true
9
2000000
1
1
0.03
true
10000000
4
0.5
action-guidance
10
0
7.21954
1
10
0
40
Finished
-
anonymous-rl-code
5h 35m 21s
-
2000000
true
1024
true
0.1
true
true
0.8
0.5
0.01
ppo_ac_positive_reward
0.8
true
0.95
0.99
MicrortsProduceCombatUnitHRL-v1
false
false
0.00025
0.5
256
4
true
8
128
1
true
6
2000000
1
1
0.03
true
10000000
4
0.5
action-guidance
10
0
7.80533
1
10
0
40
Finished
-
anonymous-rl-code
5h 37m 52s
-
2000000
true
1024
true
0.1
true
true
0.8
0.5
0.01
ppo_ac_positive_reward
0.8
true
0.95
0.99
MicrortsRandomEnemyHRL3-v1
false
false
0.00025
0.5
256
4
true
8
128
1
true
1
2000000
1
1
0.03
true
10000000
4
0.5
action-guidance
0
1
1.34046
0
0
5
2
Finished
-
anonymous-rl-code
5h 7s
-
2000000
true
1024
true
0.1
true
true
0.8
0.5
0.01
ppo_ac_positive_reward
0.8
true
0.95
0.99
MicrortsProduceCombatUnitHRL-v1
false
false
0.00025
0.5
256
4
true
8
128
1
true
10
2000000
1
1
0.03
true
10000000
4
0.5
action-guidance
10
0
8.21954
1
10
0
40
Finished
-
anonymous-rl-code
5h 37m 38s
-
2000000
true
1024
true
0.1
true
true
0.8
0.5
0.01
ppo_ac_positive_reward
0.8
true
0.95
0.99
MicrortsAttackHRL-v1
false
false
0.00025
0.5
256
4
true
8
128
1
true
3
2000000
1
1
0.03
true
10000000
4
0.5
action-guidance
11
11
8.21954
0
0
0
0
Finished
-
anonymous-rl-code
5h 58m 58s
-
2000000
true
1024
true
0.1
true
true
0.8
0.5
0.01
ppo_ac_positive_reward
0.8
true
0.95
0.99
MicrortsAttackHRL-v1
false
false
0.00025
0.5
256
4
true
8
128
1
true
9
2000000
1
1
0.03
true
10000000
4
0.5
action-guidance
11
11
8.21954
0
0
0
0
Finished
-
anonymous-rl-code
4h 29m 28s
-
2000000
true
1024
true
0.1
true
true
0.8
0.5
0.01
ppo_ac_positive_reward
0.8
true
0.95
0.99
MicrortsProduceCombatUnitHRL-v1
false
false
0.00025
0.5
256
4
true
8
128
1
true
2
2000000
1
1
0.03
true
10000000
4
0.5
action-guidance
10
0
8.21954
1
10
0
40
Finished
-
anonymous-rl-code
5h 59m 14s
-
2000000
true
1024
true
0.1
true
true
0.8
0.5
0.01
ppo_ac_positive_reward
0.8
true
0.95
0.99
MicrortsAttackHRL-v1
false
false
0.00025
0.5
256
4
true
8
128
1
true
10
2000000
1
1
0.03
true
10000000
4
0.5
action-guidance
11
11
8.21954
0
0
0
0
Finished
-
anonymous-rl-code
5h 9m 54s
-
2000000
true
1024
true
0.1
true
true
0.8
0.5
0.01
ppo_ac_positive_reward
0.8
true
0.95
0.99
MicrortsAttackHRL-v1
false
false
0.00025
0.5
256
4
true
8
128
1
true
8
2000000
1
1
0.03
true
10000000
4
0.5
action-guidance
11
11
8.21954
0
0
0
0
Finished
-
anonymous-rl-code
5h 43m 14s
-
2000000
true
1024
true
0.1
true
true
0.8
0.5
0.01
ppo_ac_positive_reward
0.8
true
0.95
0.99
MicrortsAttackHRL-v1
false
false
0.00025
0.5
256
4
true
8
128
1
true
4
2000000
1
1
0.03
true
10000000
4
0.5
action-guidance
11
11
8.21954
0
0
0
0
Finished
-
anonymous-rl-code
6h 7m 33s
-
2000000
true
1024
true
0.1
true
true
0.8
0.5
0.01
ppo_ac_positive_reward
0.8
true
0.95
0.99
MicrortsAttackHRL-v1
false
false
0.00025
0.5
256
4
true
8
128
1
true
5
2000000
1
1
0.03
true
10000000
4
0.5
action-guidance
11
11
8.21954
0
0
0
0
Finished
-
anonymous-rl-code
5h 44m 33s
-
2000000
true
1024
true
0.1
true
true
0.8
0.5
0.01
ppo_ac_positive_reward
0.8
true
0.95
0.99
MicrortsAttackHRL-v1
false
false
0.00025
0.5
256
4
true
8
128
1
true
7
2000000
1
1
0.03
true
10000000
4
0.5
action-guidance
11
11
8.21954
0
0
0
0
Finished
-
anonymous-rl-code
5h 33m 9s
-
2000000
true
1024
true
0.1
true
true
0.8
0.5
0.01
ppo_ac_positive_reward
0.8
true
0.95
0.99
MicrortsAttackHRL-v1
false
false
0.00025
0.5
256
4
true
8
128
1
true
6
2000000
1
1
0.03
true
10000000
4
0.5
action-guidance
11
11
8.21954
0
0
0
0
Finished
-
anonymous-rl-code
4h 59m 57s
-
2000000
true
1024
true
0.1
true
true
0.8
0.5
0.01
ppo_ac_positive_reward
0.8
true
0.95
0.99
MicrortsProduceCombatUnitHRL-v1
false
false
0.00025
0.5
256
4
true
8
128
1
true
5
2000000
1
1
0.03
true
10000000
4
0.5
action-guidance
10
0
7.81025
1
10
0
40
Finished
-
anonymous-rl-code
5h 57m 6s
-
2000000
true
1024
true
0.1
true
true
0.8
0.5
0.01
ppo_ac_positive_reward
0.8
true
0.95
0.99
MicrortsAttackHRL-v1
false
false
0.00025
0.5
256
4
true
8
128
1
true
1
2000000
1
1
0.03
true
10000000
4
0.5
action-guidance
11
11
8.21954
0
0
0
0
Finished
-
anonymous-rl-code
4h 56m 53s
-
2000000
true
1024
true
0.1
true
true
0.8
0.5
0.01
ppo_ac_positive_reward
0.8
true
0.95
0.99
MicrortsProduceCombatUnitHRL-v1
false
false
0.00025
0.5
256
4
true
8
128
1
true
1
2000000
1
1
0.03
true
10000000
4
0.5
action-guidance
10
0
7.80533
1
10
0
40
Finished
-
anonymous-rl-code
5h 20m 55s
-
2000000
true
1024
true
0.1
true
true
0.8
0.5
0.01
ppo_ac_positive_reward
0.8
true
0.95
0.99
MicrortsAttackHRL-v1
false
false
0.00025
0.5
256
4
true
8
128
1
true
2
2000000
1
1
0.03
true
10000000
4
0.5
action-guidance
11
11
8.21954
0
0
0
0
1-30
of 30