Norest's workspace
Runs
180
Name
180 visualized
State
Notes
User
Tags
Created
Runtime
Sweep
algorithm
algorithm_kwargs.batch_size
algorithm_kwargs.load_snapshot
algorithm_kwargs.max_path_length
algorithm_kwargs.min_num_steps_before_training
algorithm_kwargs.num_epochs
algorithm_kwargs.num_eval_steps_per_epoch
algorithm_kwargs.num_expl_steps_per_train_loop
algorithm_kwargs.num_train_loops_per_epoch
algorithm_kwargs.num_trains_per_train_loop
algorithm_kwargs.save_snapshot
algorithm_kwargs.snapshot_every
async_eval
environment
exp_name
gpu_id
layer_size
maze.inner_reward_scaling
no_depth_flag
no_gpu
penalty
random_distance_reset
random_reset
random_reset_buffer_size
random_reset_counts
random_weighted_reset
replay_buffer_size
replay_in_cuda
reset_temp
seed
train_rollout_settings.func
train_rollout_settings.r_kwargs.num_steps_down
train_rollout_settings.r_kwargs.times_repeat_each_step
trainer_kwargs.discount
trainer_kwargs.policy_lr
trainer_kwargs.qf_lr
trainer_kwargs.reward_scale
trainer_kwargs.soft_target_tau
trainer_kwargs.target_update_period
trainer_kwargs.use_automatic_entropy_tuning
tree.c_puct
tree.distance_between_nodes
tree.each_step_max_depth
tree.pw_alpha
Finished
-
norest
8s
-
SAC
256
trained_models/inst7.snp
1000
10000
3000
5000
1
1000
1
trained_models/inst7.snp
100
true
AntSeqUMazeEnv
test-exp
0
256
0
true
false
0
true
false
1000
1
false
1000000
false
4
2
each_step_tree
1
1
0.99
0.0003
0.0003
5
0.005
1
true
0.05
1
10000000000
0.5
Finished
-
norest
10s
-
SAC
256
trained_models/inst8.snp
1000
10000
3000
5000
1
1000
1
trained_models/inst8.snp
100
true
AntSeqUMazeEnv
test-exp
0
256
0
true
false
0
true
false
1000
1
false
1000000
false
4
3
each_step_tree
1
1
0.99
0.0003
0.0003
5
0.005
1
true
0.05
1
10000000000
0.5
Finished
-
norest
8s
-
SAC
256
trained_models/inst11.snp
1000
10000
3000
5000
1
1000
1
trained_models/inst11.snp
100
true
AntSeqUMazeEnv
test-exp
0
256
0
true
false
0
true
false
1000
4
false
1000000
false
1
3
each_step_tree
1
1
0.99
0.0003
0.0003
5
0.005
1
true
0.05
1
10000000000
0.5
Finished
-
norest
10s
-
SAC
256
trained_models/inst9.snp
1000
10000
3000
5000
1
1000
1
trained_models/inst9.snp
100
true
AntSeqUMazeEnv
test-exp
0
256
0
true
false
0
true
false
1000
4
false
1000000
false
1
1
each_step_tree
1
1
0.99
0.0003
0.0003
5
0.005
1
true
0.05
1
10000000000
0.5
Finished
-
norest
10s
-
SAC
256
trained_models/inst6.snp
1000
10000
3000
5000
1
1000
1
trained_models/inst6.snp
100
true
AntSeqUMazeEnv
test-exp
0
256
0
true
false
0
true
false
1000
1
false
1000000
false
4
1
each_step_tree
1
1
0.99
0.0003
0.0003
5
0.005
1
true
0.05
1
10000000000
0.5
Finished
-
norest
11s
-
SAC
256
trained_models/inst10.snp
1000
10000
3000
5000
1
1000
1
trained_models/inst10.snp
100
true
AntSeqUMazeEnv
test-exp
0
256
0
true
false
0
true
false
1000
4
false
1000000
false
1
2
each_step_tree
1
1
0.99
0.0003
0.0003
5
0.005
1
true
0.05
1
10000000000
0.5
Finished
-
norest
1d 1m 38s
-
SAC
256
trained_models/inst1.snp
1000
10000
3000
5000
1
1000
1
trained_models/inst1.snp
100
true
AntSeqUMazeEnv
test-exp
0
256
0
true
false
0
true
false
1000
1
false
1000000
false
1
2
each_step_tree
1
1
0.99
0.0003
0.0003
5
0.005
1
true
0.05
1
10000000000
0.5
Finished
-
norest
1d 1m 30s
-
SAC
256
trained_models/inst3.snp
1000
10000
3000
5000
1
1000
1
trained_models/inst3.snp
100
true
AntSeqUMazeEnv
test-exp
0
256
0
true
false
0
true
false
1000
1
false
1000000
false
2
1
each_step_tree
1
1
0.99
0.0003
0.0003
5
0.005
1
true
0.05
1
10000000000
0.5
Finished
-
norest
1d 1m 21s
-
SAC
256
trained_models/inst5.snp
1000
10000
3000
5000
1
1000
1
trained_models/inst5.snp
100
true
AntSeqUMazeEnv
test-exp
0
256
0
true
false
0
true
false
1000
1
false
1000000
false
2
3
each_step_tree
1
1
0.99
0.0003
0.0003
5
0.005
1
true
0.05
1
10000000000
0.5
Finished
-
norest
1d 1m 13s
-
SAC
256
trained_models/inst4.snp
1000
10000
3000
5000
1
1000
1
trained_models/inst4.snp
100
true
AntSeqUMazeEnv
test-exp
0
256
0
true
false
0
true
false
1000
1
false
1000000
false
2
2
each_step_tree
1
1
0.99
0.0003
0.0003
5
0.005
1
true
0.05
1
10000000000
0.5
Finished
-
norest
1d 1m 2s
-
SAC
256
trained_models/inst0.snp
1000
10000
3000
5000
1
1000
1
trained_models/inst0.snp
100
true
AntSeqUMazeEnv
test-exp
0
256
0
true
false
0
true
false
1000
1
false
1000000
false
1
1
each_step_tree
1
1
0.99
0.0003
0.0003
5
0.005
1
true
0.05
1
10000000000
0.5
Finished
-
norest
1d 51s
-
SAC
256
trained_models/inst2.snp
1000
10000
3000
5000
1
1000
1
trained_models/inst2.snp
100
true
AntSeqUMazeEnv
test-exp
0
256
0
true
false
0
true
false
1000
1
false
1000000
false
1
3
each_step_tree
1
1
0.99
0.0003
0.0003
5
0.005
1
true
0.05
1
10000000000
0.5
Finished
-
norest
1d 17s
-
SAC
256
trained_models/inst6.snp
1000
10000
3000
5000
1
1000
1
trained_models/inst6.snp
100
true
AntSeqUMazeEnv
test-exp
0
256
0
true
false
0
true
false
1000
1
false
1000000
false
4
1
each_step_tree
1
1
0.99
0.0003
0.0003
5
0.005
1
true
0.05
1
10000000000
0.5
Finished
-
norest
1d 1m 17s
-
SAC
256
trained_models/inst9.snp
1000
10000
3000
5000
1
1000
1
trained_models/inst9.snp
100
true
AntSeqUMazeEnv
test-exp
0
256
0
true
false
0
true
false
1000
4
false
1000000
false
1
1
each_step_tree
1
1
0.99
0.0003
0.0003
5
0.005
1
true
0.05
1
10000000000
0.5
Finished
-
norest
1d 41s
-
SAC
256
trained_models/inst11.snp
1000
10000
3000
5000
1
1000
1
trained_models/inst11.snp
100
true
AntSeqUMazeEnv
test-exp
0
256
0
true
false
0
true
false
1000
4
false
1000000
false
1
3
each_step_tree
1
1
0.99
0.0003
0.0003
5
0.005
1
true
0.05
1
10000000000
0.5
Finished
-
norest
1d 1m 22s
-
SAC
256
trained_models/inst8.snp
1000
10000
3000
5000
1
1000
1
trained_models/inst8.snp
100
true
AntSeqUMazeEnv
test-exp
0
256
0
true
false
0
true
false
1000
1
false
1000000
false
4
3
each_step_tree
1
1
0.99
0.0003
0.0003
5
0.005
1
true
0.05
1
10000000000
0.5
Finished
-
norest
1d 37s
-
SAC
256
trained_models/inst7.snp
1000
10000
3000
5000
1
1000
1
trained_models/inst7.snp
100
true
AntSeqUMazeEnv
test-exp
0
256
0
true
false
0
true
false
1000
1
false
1000000
false
4
2
each_step_tree
1
1
0.99
0.0003
0.0003
5
0.005
1
true
0.05
1
10000000000
0.5
Finished
-
norest
1d 1m 44s
-
SAC
256
trained_models/inst10.snp
1000
10000
3000
5000
1
1000
1
trained_models/inst10.snp
100
true
AntSeqUMazeEnv
test-exp
0
256
0
true
false
0
true
false
1000
4
false
1000000
false
1
2
each_step_tree
1
1
0.99
0.0003
0.0003
5
0.005
1
true
0.05
1
10000000000
0.5
Finished
-
norest
23h 59m 40s
-
SAC
256
trained_models/inst17.snp
1000
10000
3000
5000
1
1000
1
trained_models/inst17.snp
100
true
AntSeqUMazeEnv
test-exp
0
256
0
true
false
0
true
false
1000
4
false
1000000
false
4
3
each_step_tree
1
1
0.99
0.0003
0.0003
5
0.005
1
true
0.05
1
10000000000
0.5
Finished
-
norest
23h 59m 33s
-
SAC
256
trained_models/inst13.snp
1000
10000
3000
5000
1
1000
1
trained_models/inst13.snp
100
true
AntSeqUMazeEnv
test-exp
0
256
0
true
false
0
true
false
1000
4
false
1000000
false
2
2
each_step_tree
1
1
0.99
0.0003
0.0003
5
0.005
1
true
0.05
1
10000000000
0.5
1-20
of 180