Andrew Cohen
|
088dd213
|
Merge branch 'develop-action-buffer' of https://github.com/Unity-Technologies/ml-agents into develop-action-buffer
|
4 年前 |
GitHub
|
caac7324
|
Update ml-agents-envs/mlagents_envs/environment.py
Co-authored-by: Vincent-Pierre BERGES <vincentpierre@unity3d.com>
|
4 年前 |
|
Andrew Cohen
|
c91d1cbe
|
revert demo
|
4 年前 |
|
Andrew Cohen
|
5ec3fb98
|
fix action mask in trajectory
|
4 年前 |
|
Andrew Cohen
|
f2c9d184
|
fix set_actions_for_agent
|
4 年前 |
|
Andrew Cohen
|
453a2bba
|
ActionTuple default is now np.array, not None
|
4 年前 |
|
GitHub
|
559609a2
|
Update ml-agents/mlagents/trainers/torch/utils.py
Co-authored-by: Vincent-Pierre BERGES <vincentpierre@unity3d.com>
|
4 年前 |
|
Andrew Cohen
|
68b98915
|
Merge branch 'develop-action-buffer' of https://github.com/Unity-Technologies/ml-agents into develop-action-buffer
|
4 年前 |
|
GitHub
|
d2d46103
|
Remove print from ppo tf opti
Co-authored-by: Vincent-Pierre BERGES <vincentpierre@unity3d.com>
|
4 年前 |
|
Andrew Cohen
|
157f9e77
|
rename to ActionTuple
|
4 年前 |
|
Andrew Cohen
|
be87d69f
|
revert demo
|
4 年前 |
|
Andrew Cohen
|
e168bb4f
|
add docstrings to AgentAction and ActionLogProbs
|
4 年前 |
|
Andrew Cohen
|
43387daa
|
remove unused import
|
4 年前 |
|
Andrew Cohen
|
a545859e
|
fix torch test policy
|
4 年前 |
|
Andrew Cohen
|
e9cb1066
|
agent processor tests
|
4 年前 |
|
Andrew Cohen
|
eef14922
|
discrete/contionuous unity envs train
|
4 年前 |
|
Andrew Cohen
|
230497f5
|
fix torch utils test
|
4 年前 |
|
Andrew Cohen
|
293bd20b
|
fix torch test_ppo
|
4 年前 |
|
Andrew Cohen
|
97d94a83
|
fix test_tf_policy
|
4 年前 |
|
Andrew Cohen
|
3c65b964
|
fixed recurrent prev_action issue
|
4 年前 |
|
Andrew Cohen
|
cd73cce2
|
test_trajectory fixed
|
4 年前 |
|
Andrew Cohen
|
94179947
|
fix demo loader tests
|
4 年前 |
|
Andrew Cohen
|
762274d9
|
agent processor tests
|
4 年前 |
|
Andrew Cohen
|
73b778cc
|
rename extract to from_dict
|
4 年前 |
|
Andrew Cohen
|
b5d1c071
|
Merge branch 'master' into develop-action-buffer
|
4 年前 |
|
Andrew Cohen
|
4ebc6c44
|
ml-agents-envs pass
|
4 年前 |
|
Andrew Cohen
|
8172b3d6
|
test_simple_rl/reward providers pass tf/torch
|
4 年前 |
|
Andrew Cohen
|
dee6b805
|
fixed bug in discrete
|
4 年前 |
|
Andrew Cohen
|
24fd9b3c
|
torch reward providers all pass
|
4 年前 |
|
Andrew Cohen
|
85e4db33
|
bc tests pass
|
4 年前 |
|
Andrew Cohen
|
056630d7
|
sac continuous and discrete train
|
4 年前 |
|
Andrew Cohen
|
fcf6471e
|
2d discrete passes
|
4 年前 |
|
Andrew Cohen
|
ad951493
|
debugging discrete
|
4 年前 |
|
Andrew Cohen
|
b36fcf16
|
discrete runs/cont passes
|
4 年前 |
|
Andrew Cohen
|
bd917c9c
|
action buffer passes continuous
|
4 年前 |
|
Andrew Cohen
|
d8dd5e44
|
Merge branch 'master' into develop-action-buffer
|
4 年前 |
|
Andrew Cohen
|
f6355ba9
|
Merge branch 'develop-action-spec' into develop-action-buffer
|
4 年前 |
|
Andrew Cohen
|
c745bdd8
|
rename create empty to empty action
|
4 年前 |
|
Andrew Cohen
|
e5cc57f9
|
rename create random to random action
|
4 年前 |
|
Andrew Cohen
|
a343f4e1
|
increase seq length
|
4 年前 |
|
Andrew Cohen
|
667d295c
|
recurrent sac passes locally but fails on CI for inexplicable reasons
|
4 年前 |
|
Andrew Cohen
|
653de147
|
fix AgentExperience typing
|
4 年前 |
|
Andrew Cohen
|
b70e6078
|
reduce steps_per_update recurrent sac
|
4 年前 |
|
Andrew Cohen
|
3f771e61
|
add ActionBuffers and utils
|
4 年前 |
|
Andrew Cohen
|
95892058
|
reduce recurrent step/increase batch size
|
4 年前 |
|
Andrew Cohen
|
8df63dab
|
reduce visual advanced steps
|
4 年前 |
|
Andrew Cohen
|
4f66ebc2
|
fix recurrent sac
|
4 年前 |
|
Andrew Cohen
|
505dcf80
|
fix recurrent/advanced ppo tests
|
4 年前 |
|
Andrew Cohen
|
5b9aab58
|
fix advanced vis encoder simple rl
|
4 年前 |
|
Andrew Cohen
|
a4c3e26a
|
make validate action private
|
4 年前 |
