Skip to main content

Ctrl+K

Welcome to Tianshou!

Tutorials
Notebook Tutorials
- Overview
- Batch
- Buffer
- Vectorized Environment
- Policy
- Collector
- Trainer
- Experiment
Tianshou API Reference
- data
  - batch
  - collector
  - stats
  - types
  - buffer
    - base
    - cached
    - her
    - manager
    - prio
    - vecbuf
  - utils
    - converter
    - segtree
- env
  - gym_wrappers
  - pettingzoo_env
  - utils
  - venv_wrappers
  - venvs
  - worker
    - base
    - dummy
    - ray
    - subproc
- evaluation
  - launcher
  - rliable_evaluation_hl
- exploration
  - random
- highlevel
  - agent
  - config
  - env
  - experiment
  - logger
  - optim
  - persistence
  - trainer
  - world
  - module
    - actor
    - core
    - critic
    - intermediate
    - module_opt
    - special
  - params
    - alpha
    - dist_fn
    - env_param
    - lr_scheduler
    - noise
    - policy_params
    - policy_wrapper
- policy
  - base
  - random
  - imitation
    - base
    - bcq
    - cql
    - discrete_bcq
    - discrete_cql
    - discrete_crr
    - gail
    - td3_bc
  - modelbased
    - icm
    - psrl
  - modelfree
    - a2c
    - bdq
    - c51
    - ddpg
    - discrete_sac
    - dqn
    - fqf
    - iqn
    - npg
    - pg
    - ppo
    - qrdqn
    - rainbow
    - redq
    - sac
    - td3
    - trpo
  - multiagent
    - mapolicy
- trainer
  - base
  - utils
- utils
  - conversion
  - logging
  - lr_scheduler
  - optim
  - print
  - progress_bar
  - space_info
  - statistics
  - torch_utils
  - warning
  - logger
    - base
    - tensorboard
    - wandb
  - net
Contributing to Tianshou
- Contributors

.rst

modelfree

modelfree#

bdq
dqn
redq
trpo
td3
c51
ppo
a2c
npg
sac
qrdqn
rainbow
ddpg
discrete_sac
iqn
fqf
pg

By Tianshou contributors