Rohansi2's workspace
Runs
3
State
Notes
User
Tags
Created
Runtime
Sweep
action_bound_method
action_scaling
batch_size
buffer_size
cost_limit
deterministic_eval
device
episode_per_collect
epoch
eps_clip
gae_lambda
gamma
hidden_sizes
lagrangian_pid
last_layer_scale
logdir
lr
max_batchsize
max_grad_norm
norm_adv
prefix
project
recompute_adv
render
repeat_per_collect
rescaling
resume
rew_norm
reward_threshold
save_ckpt
save_interval
seed
step_per_epoch
suffix
target_kl
task
testing_num
thread
training_num
unbounded
use_lagrangian
value_clip
verbose
vf_coef
Finished
rohansi2
48m 34s
-
clip
true
256
100000
10
true
cpu
20
100
0.2
0.95
0.99
[128,128]
[0.05,0.0005,0.1]
false
logs
0.0005
100000
0.5
true
ppol
fast-safe-rl
false
false
4
true
false
false
10000
true
4
123
10000
0.02
SafetyCarCircle-v0
2
4
20
false
true
false
true
0.25
Finished
rohansi2
49m 49s
-
clip
true
256
100000
10
true
cpu
20
100
0.2
0.95
0.99
[128,128]
[0.05,0.0005,0.1]
false
logs
0.0005
100000
0.5
true
ppol
fast-safe-rl
false
false
4
true
false
false
10000
true
4
42
10000
0.02
SafetyCarCircle-v0
2
4
20
false
true
false
true
0.25
Finished
rohansi2
49m 42s
-
clip
true
256
100000
10
true
cpu
20
100
0.2
0.95
0.99
[128,128]
[0.05,0.0005,0.1]
false
logs
0.0005
100000
0.5
true
ppol
fast-safe-rl
false
false
4
true
false
false
10000
true
4
10
10000
0.02
SafetyCarCircle-v0
2
4
20
false
true
false
true
0.25
1-3
of 3