Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

PPO #28

Open
wants to merge 11 commits into
base: main
Choose a base branch
from
Open

PPO #28

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
11 commits
Select commit Hold shift + click to select a range
f85e195
:poop: Adiciona notebook de PPO
nelsonayamashita Nov 1, 2020
a70ad4f
:fire: Remove arquivos de configuraçao do vscode
fernandokm Nov 1, 2020
c56ed7a
:hammer: Arruma docstrings e PPO.train()
nelsonayamashita Nov 3, 2020
b947630
:art: Adiciona diagrama do clip
nelsonayamashita Nov 3, 2020
c9eccd1
:bug: Arruma typo
fernandokm Nov 6, 2020
356c18e
:sparkles: Adiciona README
nelsonayamashita Jan 18, 2021
61f42f3
Troca nomes de classes para on-p
nelsonayamashita Jun 25, 2021
f30532a
Merge branch 'master' into PPO
nelsonayamashita Jun 25, 2021
c8c7834
:art: Arruma estrutura da pasta e texto de PPO
nelsonayamashita Jun 25, 2021
f92e7a2
:memo: Melhora os nomes para on-policy
nelsonayamashita Jun 25, 2021
bc67529
Apply suggestions from code review
Berbardo Sep 23, 2021
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
24 changes: 12 additions & 12 deletions Aprendizado por Reforço Profundo/Actor-Critic/A2C/A2C.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -229,7 +229,7 @@
"id": "1ZiSoaCSnX-3"
},
"source": [
"## Experience Replay"
"## Memory Buffer"
]
},
{
Expand All @@ -242,8 +242,8 @@
"source": [
"import numpy as np\n",
"\n",
"class ExperienceReplay:\n",
" \"\"\"Experience Replay Buffer para A2C.\"\"\"\n",
"class MemoryBuffer:\n",
" \"\"\"Memory Buffer Buffer para A2C.\"\"\"\n",
" def __init__(self, max_length, observation_space):\n",
" \"\"\"Cria um Replay Buffer.\n",
"\n",
Expand Down Expand Up @@ -286,7 +286,7 @@
" self.dones[self.length] = dones\n",
" self.length += 1\n",
"\n",
" def sample(self):\n",
" def get_batch(self):\n",
" \"\"\"Retorna um batch de experiências.\n",
" \n",
" Parâmetros\n",
Expand Down Expand Up @@ -340,7 +340,7 @@
" self.entropy_coef = entropy_coef\n",
"\n",
" self.n_steps = n_steps\n",
" self.memory = ExperienceReplay(n_steps, observation_space.shape[0])\n",
" self.memory = MemoryBuffer(n_steps, observation_space.shape[0])\n",
"\n",
" self.actor = Actor(observation_space.shape[0], action_space.n).to(self.device)\n",
" self.critic = Critic(observation_space.shape[0]).to(self.device)\n",
Expand Down Expand Up @@ -380,7 +380,7 @@
" if self.memory.length < self.n_steps:\n",
" return\n",
"\n",
" (states, actions, rewards, next_states, dones) = self.memory.sample()\n",
" (states, actions, rewards, next_states, dones) = self.memory.get_batch()\n",
"\n",
" states = torch.FloatTensor(states).to(self.device)\n",
" actions = torch.FloatTensor(actions).to(self.device)\n",
Expand Down Expand Up @@ -664,7 +664,7 @@
" self.entropy_coef = entropy_coef\n",
"\n",
" self.n_steps = n_steps\n",
" self.memory = ExperienceReplay(n_steps, observation_space.shape[0])\n",
" self.memory = MemoryBuffer(n_steps, observation_space.shape[0])\n",
"\n",
" self.actorcritic = ActorCritic(observation_space.shape[0], action_space.n).to(self.device)\n",
" self.actorcritic_optimizer = optim.Adam(self.actorcritic.parameters(), lr=lr)\n",
Expand Down Expand Up @@ -702,7 +702,7 @@
" if self.memory.length < self.n_steps:\n",
" return\n",
"\n",
" (states, actions, rewards, next_states, dones) = self.memory.sample()\n",
" (states, actions, rewards, next_states, dones) = self.memory.get_batch()\n",
"\n",
" states = torch.FloatTensor(states).to(self.device)\n",
" actions = torch.FloatTensor(actions).to(self.device)\n",
Expand Down Expand Up @@ -869,7 +869,7 @@
"source": [
"import numpy as np\n",
"\n",
"class MultipleExperienceReplay:\n",
"class MultipleMemoryBuffer:\n",
" def __init__(self, max_length, env_num, observation_space):\n",
" self.length = 0\n",
" self.max_length = max_length\n",
Expand All @@ -888,7 +888,7 @@
" self.dones[self.length] = dones\n",
" self.length += 1\n",
"\n",
" def sample(self):\n",
" def get_batch(self):\n",
" self.length = 0\n",
"\n",
" return (self.states, self.actions, self.rewards, self.next_states, self.dones)"
Expand Down Expand Up @@ -944,7 +944,7 @@
" self.entropy_coef = entropy_coef\n",
"\n",
" self.n_steps = n_steps\n",
" self.memory = MultipleExperienceReplay(n_steps, env_num, observation_space.shape[0])\n",
" self.memory = MultipleMemoryBuffer(n_steps, env_num, observation_space.shape[0])\n",
"\n",
" self.actorcritic = ActorCritic(observation_space.shape[0], action_space.n).to(self.device)\n",
" self.actorcritic_optimizer = optim.Adam(self.actorcritic.parameters(), lr=lr)\n",
Expand Down Expand Up @@ -982,7 +982,7 @@
" if self.memory.length < self.n_steps:\n",
" return\n",
"\n",
" (states, actions, rewards, next_states, dones) = self.memory.sample()\n",
" (states, actions, rewards, next_states, dones) = self.memory.get_batch()\n",
"\n",
" states = torch.FloatTensor(states).to(self.device)\n",
" actions = torch.FloatTensor(actions).to(self.device)\n",
Expand Down
Loading