PyBullet and Other Continuous Action Tasks
Learn to perform robotics tasks with bullet3 physics engine
Created on July 25|Last edited on July 2
Comment
InvertedDoublePendulumBulletEnv-v0
charts/episode_reward
charts/episode_reward
exp_name: ddpg_continuous_action
exp_name: td3_continuous_action
exp_name: ppo_continuous_action
Walker2DBulletEnv-v0
This run didn't log media for key "video.0", step 22250, index 0. Docs →
This run didn't log media for key "video.0", step 17261, index 0. Docs →
This run didn't log media for key "video.0", step 23142, index 0. Docs →
This run didn't log media for key "video.0", step 24823, index 0. Docs →
This run didn't log media for key "video.0", step 3719, index 0. Docs →
This run didn't log media for key "video.0", step 3856, index 0. Docs →
Run set
6
Name
6 visualized
State
Notes
User
Tags
Created
Runtime
alpha
autotune
batch_size
buffer_size
capture_video
clip_coef
cuda
end_e
ent_coef
episode_length
exp_name
exploration_fraction
gamma
gym_id
learning_rate
max_grad_norm
milestone
notb
policy_hid_sizes
prod_mode
q_hid_sizes
seed
start_e
target_network_frequency
target_update_interval
tau
torch_deterministic
total_timesteps
update_epochs
value_hid_sizes
vf_coef
wandb_entity
wandb_project_name
action_noise
actor_buffer_size
alpha_lr
anneal_lr
aux_batch_size
aux_minibatch_size
beta_clone
bias_init
buffer_name
clip_vloss
e_auxiliary
e_policy
Finished
costa-huang
12h 8m 47s
-
-
256
1000000
true
-
true
-
-
0
ddpg_continuous_action
-
0.99
InvertedDoublePendulumBulletEnv-v0
0.0003
0.5
-
-
-
true
-
2
-
-
-
0.005
true
2000000
-
-
-
cleanrl
cleanrl.benchmark
-
-
-
-
-
-
-
-
-
-
-
-
Finished
costa-huang
12h 5m 39s
-
-
256
1000000
true
-
true
-
-
0
ddpg_continuous_action
-
0.99
InvertedDoublePendulumBulletEnv-v0
0.0003
0.5
-
-
-
true
-
1
-
-
-
0.005
true
2000000
-
-
-
cleanrl
cleanrl.benchmark
-
-
-
-
-
-
-
-
-
-
-
-
Finished
costa-huang
13h 26m 24s
-
-
256
1000000
true
-
true
-
-
0
td3_continuous_action
-
0.99
InvertedDoublePendulumBulletEnv-v0
0.0003
0.5
-
-
-
true
-
2
-
-
-
0.005
true
2000000
-
-
-
cleanrl
cleanrl.benchmark
-
-
-
-
-
-
-
-
-
-
-
-
Finished
costa-huang
13h 20m 6s
-
-
256
1000000
true
-
true
-
-
0
td3_continuous_action
-
0.99
InvertedDoublePendulumBulletEnv-v0
0.0003
0.5
-
-
-
true
-
1
-
-
-
0.005
true
2000000
-
-
-
cleanrl
cleanrl.benchmark
-
-
-
-
-
-
-
-
-
-
-
-
Finished
costa-huang
43m 30s
-
-
2048
-
true
0.2
true
-
0
-
ppo_continuous_action
-
0.99
InvertedDoublePendulumBulletEnv-v0
0.0003
0.5
-
-
-
true
-
2
-
-
-
-
true
2000000
10
-
0.5
cleanrl
cleanrl.benchmark
-
-
-
true
-
-
-
-
-
true
-
-
Finished
costa-huang
1h 18m 38s
-
-
2048
-
true
0.2
true
-
0
-
ppo_continuous_action
-
0.99
InvertedDoublePendulumBulletEnv-v0
0.0003
0.5
-
-
-
true
-
1
-
-
-
-
true
2000000
10
-
0.5
cleanrl
cleanrl.benchmark
-
-
-
true
-
-
-
-
-
true
-
-
1-6
of 6
MinitaurBulletDuckEnv-v0
Run set
6
AntBulletEnv-v0
Run set
8
HopperBulletEnv-v0
Run set
8
InvertedPendulumBulletEnv-v0
Run set
6
MinitaurBulletEnv-v0
Run set
6
PusherBulletEnv-v0
Run set
2
Walker2DBulletEnv-v0
Run set
8
HalfCheetahBulletEnv-v0
Run set
8
ReacherBulletEnv-v0
Run set
2
HumanoidBulletEnv-v0
Run set
8
Pendulum-v0
Run set
8
LunarLanderContinuous-v2
Run set
8
MountainCarContinuous-v0
Run set
8
BipedalWalker-v3
Run set
6
Add a comment
Created with ❤️ on Weights & Biases.
https://wandb.ai/cleanrl/cleanrl.benchmark/reports/PyBullet-and-Other-Continuous-Action-Tasks--VmlldzoxODE0NzY