Documentation
¶
Overview ¶
Package agent provides the agent implementations and base tooling.
Index ¶
Constants ¶
This section is empty.
Variables ¶
This section is empty.
Functions ¶
func WithLogger ¶
WithLogger adds a logger to the base.
func WithTracker ¶
WithTracker sets the tracker being used by the agent
func WithoutServer ¶
func WithoutServer() func(*Base)
WithoutServer will prevent the provisioning of a server for the agent.
func WithoutTracker ¶
func WithoutTracker() func(*Base)
WithoutTracker prevents tracker from being created.
Types ¶
type Base ¶
type Base struct {
// Name of the agent.
Name string
// Port agent is serving on.
Port string
// Tracker for the agent.
Tracker *track.Tracker
// Logger for the agent.
Logger *log.Logger
// contains filtered or unexported fields
}
Base is an agents base functionality.
func (*Base) ApplyHandlers ¶
ApplyHandlers adds the base handlers.
func (*Base) InfoHandler ¶
func (b *Base) InfoHandler(w http.ResponseWriter, req *http.Request)
InfoHandler returns info about the agent.
func (*Base) MakeEpisodes ¶
MakeEpisodes creates a set of episodes for training and stores the number for configuration.
Directories
¶
| Path | Synopsis |
|---|---|
|
Package deepq is an agent implementation of the DeepQ algorithm.
|
Package deepq is an agent implementation of the DeepQ algorithm. |
|
experiments/cartpole
command
|
|
|
experiments/pong
command
|
|
|
Package her is an agent implementation of the Hindsight Experience Replay algorithm.
|
Package her is an agent implementation of the Hindsight Experience Replay algorithm. |
|
experiments/bitflip
command
|
|
|
Package nes is an agent implementation of the Natural Evolution Strategies algorithm.
|
Package nes is an agent implementation of the Natural Evolution Strategies algorithm. |
|
experiments/cartpole
command
|
|
|
Package ppo is an agent implementation of the Proximal Policy Optimization algorithm.
|
Package ppo is an agent implementation of the Proximal Policy Optimization algorithm. |
|
experiments/cartpole
command
|
|
|
Package q is an agent implementation of the Q learning algorithm.
|
Package q is an agent implementation of the Q learning algorithm. |
|
experiments/taxi
command
|
|
|
Package reinforce is an agent implementation of the REINFORCE algorithm.
|
Package reinforce is an agent implementation of the REINFORCE algorithm. |
|
experiments/cartpole
command
|
Click to show internal directories.
Click to hide internal directories.