Skip to main content
Ctrl+K
Tianshou Documentation - Home
  • Welcome to Tianshou!
  • User Guide
    • The Reinforcement Learning Process
    • Dual APIs
    • Core Abstractions
  • Deep Dives
    • Batch: Tianshou’s Core Data Structure
    • Buffer: Experience Replay in Tianshou
    • Environments
    • Generalized Advantage Estimation
    • Collector
    • Multi-Agent Reinforcement Learning (MARL)
  • Tianshou API Reference
    • config
    • trainer
    • algorithm
      • algorithm_base
      • optim
      • random
      • imitation
        • bcq
        • cql
        • discrete_bcq
        • discrete_cql
        • discrete_crr
        • gail
        • imitation_base
        • td3_bc
      • modelbased
        • icm
        • psrl
      • modelfree
        • a2c
        • bdqn
        • c51
        • ddpg
        • discrete_sac
        • dqn
        • fqf
        • iqn
        • npg
        • ppo
        • qrdqn
        • rainbow
        • redq
        • reinforce
        • sac
        • td3
        • trpo
      • multiagent
        • marl
    • data
      • batch
      • collector
      • stats
      • types
      • buffer
        • buffer_base
        • cached
        • her
        • manager
        • prio
        • vecbuf
      • utils
        • converter
        • segtree
    • env
      • gym_wrappers
      • pettingzoo_env
      • utils
      • venv_wrappers
      • venvs
      • atari
        • atari_network
        • atari_wrapper
      • worker
        • dummy
        • ray
        • subproc
        • worker_base
    • evaluation
      • launcher
      • rliable_evaluation
    • exploration
      • random
    • highlevel
      • algorithm
      • config
      • env
      • experiment
      • logger
      • persistence
      • trainer
      • world
      • module
        • actor
        • core
        • critic
        • intermediate
        • special
      • params
        • algorithm_params
        • algorithm_wrapper
        • alpha
        • collector
        • dist_fn
        • env_param
        • lr_scheduler
        • noise
        • optim
    • utils
      • conversion
      • determinism
      • lagged_network
      • logging
      • print
      • progress_bar
      • space_info
      • statistics
      • torch_utils
      • warning
      • logger
        • logger_base
        • tensorboard
        • wandb
      • net
        • common
        • continuous
        • discrete
  • Benchmarks
  • Developer Guide
  • Contributors
  • .rst

utils

utils#

  • determinism

  • space_info

  • torch_utils

  • logging

  • conversion

  • warning

  • lagged_network

  • progress_bar

  • statistics

  • print

  • net

  • logger

previous

optim

next

conversion

By Tianshou contributors

© Copyright 2020, Tianshou contributors..