gryf/coach
1
0
Fork 0
mirror of https://github.com/gryf/coach.git synced 2025-12-17 19:20:19 +01:00
Code Issues Projects Releases Wiki Activity

parameter noise exploration - using Noisy Nets

Browse Source
This commit is contained in:
Gal Leibovich
2018-08-27 18:19:01 +03:00
parent 658b437079
commit 1aa2ab0590
49 changed files with 536 additions and 433 deletions
Download Patch File Download Diff File Expand all files Collapse all files

13
rl_coach/agents/bootstrapped_dqn_agent.py
View File

@@ -18,9 +18,11 @@ from typing import Union
import numpy as np
from rl_coach.agents.dqn_agent import DQNAgentParameters, DQNNetworkParameters
from rl_coach.agents.dqn_agent import DQNNetworkParameters, DQNAlgorithmParameters
from rl_coach.agents.value_optimization_agent import ValueOptimizationAgent
from rl_coach.base_parameters import AgentParameters
from rl_coach.exploration_policies.bootstrapped import BootstrappedParameters
from rl_coach.memories.non_episodic.experience_replay import ExperienceReplayParameters
class BootstrappedDQNNetworkParameters(DQNNetworkParameters):
@@ -30,11 +32,12 @@ class BootstrappedDQNNetworkParameters(DQNNetworkParameters):
self.rescale_gradient_from_head_by_factor = [1.0/self.num_output_head_copies]*self.num_output_head_copies
class BootstrappedDQNAgentParameters(DQNAgentParameters):
class BootstrappedDQNAgentParameters(AgentParameters):
def __init__(self):
super().__init__()
self.network_wrappers = {"main": BootstrappedDQNNetworkParameters()}
self.exploration = BootstrappedParameters()
super().__init__(algorithm=DQNAlgorithmParameters(),
exploration=BootstrappedParameters(),
memory=ExperienceReplayParameters(),
networks={"main": BootstrappedDQNNetworkParameters()})
@property
def path(self):