Alirkay's workspace
Runs
170
State
Notes
User
Tags
Created
Runtime
Sweep
agent.kwargs.action_noise
agent.kwargs.actor_net.kwargs.hidden_units
agent.kwargs.actor_net.name
agent.kwargs.actor_optimizer_fn.kwargs.lr
agent.kwargs.actor_optimizer_fn.name
agent.kwargs.atoms
agent.kwargs.batch_size
agent.kwargs.critic_net.kwargs.hidden_units
agent.kwargs.critic_net.name
agent.kwargs.critic_optimizer_fn.kwargs.lr
agent.kwargs.critic_optimizer_fn.name
agent.kwargs.device
agent.kwargs.discount_rate
agent.kwargs.distributional
agent.kwargs.double
agent.kwargs.dueling
agent.kwargs.epsilon_schedule.kwargs.end_value
agent.kwargs.epsilon_schedule.kwargs.init_value
agent.kwargs.epsilon_schedule.kwargs.steps
agent.kwargs.epsilon_schedule.name
agent.kwargs.grad_clip
agent.kwargs.id
agent.kwargs.init_fn.kwargs.scale
agent.kwargs.init_fn.name
agent.kwargs.log_frequency
agent.kwargs.loss_fn.name
agent.kwargs.min_replay_history
agent.kwargs.n_step
agent.kwargs.noisy
agent.kwargs.optimizer_fn.kwargs.alpha
agent.kwargs.optimizer_fn.kwargs.centered
agent.kwargs.optimizer_fn.kwargs.eps
agent.kwargs.optimizer_fn.kwargs.lr
agent.kwargs.optimizer_fn.name
agent.kwargs.replay_buffer.kwargs.capacity
agent.kwargs.replay_buffer.kwargs.gamma
agent.kwargs.replay_buffer.kwargs.n_step
agent.kwargs.replay_buffer.kwargs.stack_size
agent.kwargs.replay_buffer.name
agent.kwargs.representation_net.kwargs.channels
agent.kwargs.representation_net.kwargs.kernel_sizes
agent.kwargs.representation_net.kwargs.mlp_layers
agent.kwargs.representation_net.kwargs.paddings
agent.kwargs.representation_net.kwargs.strides
Finished
prishruit
benchmark
1d 21h 42m 8s
-
-
-
-
-
-
51
32
-
-
-
-
cuda
0.99
true
false
false
0.01
1
250000
LinearSchedule
-
-
0.57735
variance_scaling
1000
MSELoss
20000
3
false
-
-
0.00015
0.0000625
Adam
1000000
0.99
3
4
PrioritizedReplayBuffer
[32,64,64]
[8,4,3]
[512]
[2,2,1]
[4,2,1]
Finished
prishruit
benchmark
1d 20h 49m 29s
-
-
-
-
-
-
51
32
-
-
-
-
cuda
0.99
true
false
false
0.01
1
250000
LinearSchedule
-
-
0.57735
variance_scaling
1000
MSELoss
20000
3
false
-
-
0.00015
0.0000625
Adam
1000000
0.99
3
4
PrioritizedReplayBuffer
[32,64,64]
[8,4,3]
[512]
[2,2,1]
[4,2,1]
Finished
prishruit
benchmark
1d 19h 46m 35s
-
-
-
-
-
-
51
32
-
-
-
-
cuda
0.99
true
false
false
0.01
1
250000
LinearSchedule
-
-
0.57735
variance_scaling
1000
MSELoss
20000
3
false
-
-
0.00015
0.0000625
Adam
1000000
0.99
3
4
PrioritizedReplayBuffer
[32,64,64]
[8,4,3]
[512]
[2,2,1]
[4,2,1]
Finished
prishruit
benchmark
1d 19h 59m 16s
-
-
-
-
-
-
51
32
-
-
-
-
cuda
0.99
true
false
false
0.01
1
250000
LinearSchedule
-
-
0.57735
variance_scaling
1000
MSELoss
20000
3
false
-
-
0.00015
0.0000625
Adam
1000000
0.99
3
4
PrioritizedReplayBuffer
[32,64,64]
[8,4,3]
[512]
[2,2,1]
[4,2,1]
Finished
prishruit
benchmark
1d 21h 41m 31s
-
-
-
-
-
-
51
32
-
-
-
-
cuda
0.99
true
false
false
0.01
1
250000
LinearSchedule
-
-
0.57735
variance_scaling
1000
MSELoss
20000
3
false
-
-
0.00015
0.0000625
Adam
1000000
0.99
3
4
PrioritizedReplayBuffer
[32,64,64]
[8,4,3]
[512]
[2,2,1]
[4,2,1]
Finished
prishruit
benchmark
1d 19h 33m 50s
-
-
-
-
-
-
51
32
-
-
-
-
cuda
0.99
true
false
false
0.01
1
250000
LinearSchedule
-
-
0.57735
variance_scaling
1000
MSELoss
20000
3
false
-
-
0.00015
0.0000625
Adam
1000000
0.99
3
4
PrioritizedReplayBuffer
[32,64,64]
[8,4,3]
[512]
[2,2,1]
[4,2,1]
Finished
prishruit
benchmark
1d 19h 54m 39s
-
-
-
-
-
-
51
32
-
-
-
-
cuda
0.99
true
false
false
0.01
1
250000
LinearSchedule
-
-
0.57735
variance_scaling
1000
MSELoss
20000
3
false
-
-
0.00015
0.0000625
Adam
1000000
0.99
3
4
PrioritizedReplayBuffer
[32,64,64]
[8,4,3]
[512]
[2,2,1]
[4,2,1]
Finished
prishruit
benchmark
1d 20h 2m 54s
-
-
-
-
-
-
51
32
-
-
-
-
cuda
0.99
true
false
false
0.01
1
250000
LinearSchedule
-
-
0.57735
variance_scaling
1000
MSELoss
20000
3
false
-
-
0.00015
0.0000625
Adam
1000000
0.99
3
4
PrioritizedReplayBuffer
[32,64,64]
[8,4,3]
[512]
[2,2,1]
[4,2,1]
Finished
prishruit
benchmark
1d 19h 7m 45s
-
-
-
-
-
-
51
32
-
-
-
-
cuda
0.99
true
false
false
0.01
1
250000
LinearSchedule
-
-
0.57735
variance_scaling
1000
MSELoss
20000
3
false
-
-
0.00015
0.0000625
Adam
1000000
0.99
3
4
PrioritizedReplayBuffer
[32,64,64]
[8,4,3]
[512]
[2,2,1]
[4,2,1]
Finished
prishruit
benchmark
1d 20h 42m 16s
-
-
-
-
-
-
51
32
-
-
-
-
cuda
0.99
true
false
false
0.01
1
250000
LinearSchedule
-
-
0.57735
variance_scaling
1000
MSELoss
20000
3
false
-
-
0.00015
0.0000625
Adam
1000000
0.99
3
4
PrioritizedReplayBuffer
[32,64,64]
[8,4,3]
[512]
[2,2,1]
[4,2,1]
Finished
prishruit
benchmark
1d 20h 50m 39s
-
-
-
-
-
-
51
32
-
-
-
-
cuda
0.99
true
false
false
0.01
1
250000
LinearSchedule
-
-
0.57735
variance_scaling
1000
MSELoss
20000
3
false
-
-
0.00015
0.0000625
Adam
1000000
0.99
3
4
PrioritizedReplayBuffer
[32,64,64]
[8,4,3]
[512]
[2,2,1]
[4,2,1]
Finished
prishruit
benchmark
1d 22h 18m 13s
-
-
-
-
-
-
51
32
-
-
-
-
cuda
0.99
true
false
false
0.01
1
250000
LinearSchedule
-
-
0.57735
variance_scaling
1000
MSELoss
20000
3
false
-
-
0.00015
0.0000625
Adam
1000000
0.99
3
4
PrioritizedReplayBuffer
[32,64,64]
[8,4,3]
[512]
[2,2,1]
[4,2,1]
Finished
prishruit
benchmark
1d 23h 49m 2s
-
-
-
-
-
-
51
32
-
-
-
-
cuda
0.99
true
false
false
0.01
1
250000
LinearSchedule
-
-
0.57735
variance_scaling
1000
MSELoss
20000
3
false
-
-
0.00015
0.0000625
Adam
1000000
0.99
3
4
PrioritizedReplayBuffer
[32,64,64]
[8,4,3]
[512]
[2,2,1]
[4,2,1]
Finished
prishruit
benchmark
1d 21h 52m 48s
-
-
-
-
-
-
51
32
-
-
-
-
cuda
0.99
true
false
false
0.01
1
250000
LinearSchedule
-
-
0.57735
variance_scaling
1000
MSELoss
20000
3
false
-
-
0.00015
0.0000625
Adam
1000000
0.99
3
4
PrioritizedReplayBuffer
[32,64,64]
[8,4,3]
[512]
[2,2,1]
[4,2,1]
Finished
prishruit
benchmark
1d 21h 31m 57s
-
-
-
-
-
-
51
32
-
-
-
-
cuda
0.99
true
false
false
0.01
1
250000
LinearSchedule
-
-
0.57735
variance_scaling
1000
MSELoss
20000
3
false
-
-
0.00015
0.0000625
Adam
1000000
0.99
3
4
PrioritizedReplayBuffer
[32,64,64]
[8,4,3]
[512]
[2,2,1]
[4,2,1]
Finished
prishruit
benchmark
1d 21h 22m 44s
-
-
-
-
-
-
51
32
-
-
-
-
cuda
0.99
true
false
false
0.01
1
250000
LinearSchedule
-
-
0.57735
variance_scaling
1000
MSELoss
20000
3
false
-
-
0.00015
0.0000625
Adam
1000000
0.99
3
4
PrioritizedReplayBuffer
[32,64,64]
[8,4,3]
[512]
[2,2,1]
[4,2,1]
Finished
prishruit
benchmark
1d 22h 59s
-
-
-
-
-
-
51
32
-
-
-
-
cuda
0.99
true
false
false
0.01
1
250000
LinearSchedule
-
-
0.57735
variance_scaling
1000
MSELoss
20000
3
false
-
-
0.00015
0.0000625
Adam
1000000
0.99
3
4
PrioritizedReplayBuffer
[32,64,64]
[8,4,3]
[512]
[2,2,1]
[4,2,1]
Finished
prishruit
benchmark
1d 21h 52m
-
-
-
-
-
-
51
32
-
-
-
-
cuda
0.99
true
false
false
0.01
1
250000
LinearSchedule
-
-
0.57735
variance_scaling
1000
MSELoss
20000
3
false
-
-
0.00015
0.0000625
Adam
1000000
0.99
3
4
PrioritizedReplayBuffer
[32,64,64]
[8,4,3]
[512]
[2,2,1]
[4,2,1]
Finished
prishruit
benchmark
1d 21h 40m 16s
-
-
-
-
-
-
51
32
-
-
-
-
cuda
0.99
true
false
false
0.01
1
250000
LinearSchedule
-
-
0.57735
variance_scaling
1000
MSELoss
20000
3
false
-
-
0.00015
0.0000625
Adam
1000000
0.99
3
4
PrioritizedReplayBuffer
[32,64,64]
[8,4,3]
[512]
[2,2,1]
[4,2,1]
Finished
prishruit
benchmark
1d 21h 30m 50s
-
-
-
-
-
-
51
32
-
-
-
-
cuda
0.99
true
false
false
0.01
1
250000
LinearSchedule
-
-
0.57735
variance_scaling
1000
MSELoss
20000
3
false
-
-
0.00015
0.0000625
Adam
1000000
0.99
3
4
PrioritizedReplayBuffer
[32,64,64]
[8,4,3]
[512]
[2,2,1]
[4,2,1]
1-20
of 170