Agent.h 文件参考

#include "common/Export.h"
#include "common/Result.h"
#include <cstdint>
#include <string>
#include <vector>

浏览源代码.

类
struct	eve::agent::Observation
	Owning state projection; action IDs index a fixed domain action catalogue. 更多...
class	eve::agent::IEnvironment
	Adapter for a resettable game, simulation, UI or other decision-making environment. @ownership The caller owns the environment and all domain state. The runner borrows it only for the synchronous call; no references escape. @thread Call on the domain owner thread. Callbacks may call unrelated services, but must not reenter or destroy this environment. The runner holds no locks. 更多...
struct	eve::agent::Config
	Bounded search configuration; seed streams for environment, search and learning are separate. 更多...
struct	eve::agent::TraceStep
	Owning executed action and resulting observation; no domain pointers are retained. 更多...
struct	eve::agent::Trace
	In-memory versioned replay evidence, independent of learned model state. 更多...
struct	eve::agent::Policy
	Owning version-1 portable network weights; import validates the entire value before use. 更多...
class	eve::agent::IPolicyBackend
	Optional inference service. Providers own their registration and revoke before destruction. @thread Owner thread only; no reentry, provider unload or external callbacks during inference. @ownership Inputs are borrowed only for the call. Outputs own all data. Core resolves the capability anew for each inference; it never retains a provider across environment callbacks. 更多...
class	eve::agent::IGpuPolicyBackend
	Optional GPU policy service, registered independently of eager tensor CPU. @ownership Same synchronous borrowing contract as IPolicyBackend; revoke before destruction. @thread Device owner thread only. No callbacks, reentry or device teardown during a call. 更多...
struct	eve::agent::Report
	Owning search result; reward, coverage and failures remain separate evidence. 更多...

命名空间
namespace	eve
	Build metadata (engine git commit, build time, third-party version).
namespace	eve::agent

枚举
enum class	eve::agent::Outcome { eve::agent::Running , eve::agent::Success , eve::agent::Failure }
	Domain outcome, independent of reward and infrastructure errors. 更多...
enum class	eve::agent::Strategy { eve::agent::Random , eve::agent::EvolutionLearning }
	Explicit algorithm choice, also used for equal-budget random baselines. 更多...
enum class	eve::agent::Backend { eve::agent::Cpu , eve::agent::Tensor , eve::agent::Gpu }
	Explicit backend; Tensor is eager CPU, Gpu accelerates inference and SGD via agent_tensor. 更多...

函数
Result< void >	eve::agent::validatePolicy (const Policy &policy)
	Validate the complete owning policy before inference/import, with no mutation or callbacks.
Result< std::string >	eve::agent::backendName (Backend backend)
	Return an owning backend label, or Unsupported if Tensor is unavailable; owner thread only.
Result< Report >	eve::agent::run (const Config &config, IEnvironment &environment)
	Run bounded evolutionary rollout search and elite policy distillation.
Result< std::vector< double > >	eve::agent::infer (const Policy &policy, const Observation &observation, Backend backend=Backend::Cpu)
	Compute masked action probabilities with validated version-1 owning weights.
Result< void >	eve::agent::replay (const Trace &trace, IEnvironment &environment, double absoluteTolerance=1e-6)
	Reset and replay actual actions, checking all observations and failure evidence.