Comments (3)
A more minimalistic example is
from agentnet.memory import LSTMCell
from agentnet.target_network import TargetNetwork
from lasagne.layers import InputLayer
prev_cell, prev_out = InputLayer((None, 512)), InputLayer((None, 512))
_, new_out = LSTMCell(prev_cell, prev_out, name='lstm')
targetnet = TargetNetwork(new_out)
or
from agentnet.memory import LSTMCell
from lasagne.layers import InputLayer
from copy import deepcopy
prev_cell, prev_out = InputLayer((None, 512)), InputLayer((None, 512))
_, new_out = LSTMCell(prev_cell, prev_out, name='lstm')
memo = {}
memo[id(prev_cell)] = prev_cell
memo[id(prev_out)] = prev_out
deepcopy(new_out, memo=memo)
or yet lower:
from agentnet.memory import LSTMCell, GateLayer
from agentnet.utils.format import check_list
from lasagne.layers import InputLayer
import lasagne
from copy import deepcopy
prev_cell, prev_out = InputLayer((None, 512)), InputLayer((None, 512))
_, new_out = LSTMCell(prev_cell, prev_out, name='lstm')
gates = GateLayer([prev_out] + check_list(tuple()),
[prev_cell.output_shape[1]] * 4,
channel_names=["to_ingate", "to_forgetgate", "to_cell", "to_outgate"],
gate_nonlinearities=None,
bias_init=lasagne.init.Constant(),
weight_init=lasagne.init.Normal(),
name='')
deepcopy(gates)
from agentnet.
Figured this out, will send PR shortly.
from agentnet.
Thank you! Merged PR.
from agentnet.
Related Issues (20)
- Original DQN Example HOT 1
- Deprecation list
- Dockerfile aka "makeitwork"
- Hierarchical MDP as a demo?
- Brief outline of modules HOT 3
- AgentNet recurrence won't compile if batch_size = 1 and unroll_scan=False and at least one input is a single-element vector. HOT 2
- canonicalize LSTM HOT 3
- example:Qlearning with normalized advantage functions HOT 1
- grad dtypes mismatch in some rare case HOT 2
- better weights management for memory layers
- DPG refactor and demo HOT 1
- Vectorized environment
- deprecate preprocess_observation HOT 1
- BaseResolver returns int64 HOT 1
- Support both Theano (Lasagne; Keras) and Tensorflow (Keras) backend HOT 1
- policy_estimators param is weird HOT 3
- batch_size parameter is wierd HOT 1
- Destination GpuArray is not contiguous HOT 5
- attention tests HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from agentnet.