PPO One Step
Environment Requirements
env
: Must be registered insdriving.environments.REGISTRY
. Thestep
function must return the Reward Tensor of sizeN x 1
. By design it will assume the horizon is of size 1. This model will most likely never converge for any other horizon size.env_params
: These are passed toenv
asenv(**env_params)
. So, ensure compatibility with the corresponding environment.
Logging / Checkpointing
log_dir
: Path to the directory for storing the logs, and checkpointswandb_id
: Id with which to log in wandb. If the id is same as one before, it will append the logs to itload_path
: Checkpoint from which to load a previously trained modelsave_freq
: The frequency with which to checkpoint models
Configurable HyperParameters
actor_kwargs
: Arguments passed toPPOWaypointCategoricalActor/PPOWaypointGaussianActor
.observation_space
andaction_space
are automatically passed from theenv
, so no need to pass thoseseed
: Random Seedsteps_per_epoch
: Number of observation and action pairs to be collected before training the model. This is split equally across all the processesepochs
: Total epochsgamma
: Discount Factorclip_ratio
: Clip Ratio in the PPO Algorithmpi_lr
: Learning Rate for the Actortrain_pi_iters
: Total number of times the same set of data is passed for trainingentropy_coeff
: Coefficient for entropy regularizationlam
: Lambda for GAE-Lambda. (Always between 0 and 1, close to 1.)target_kl
: Roughly what KL divergence we think is appropriate between new and old policies after an update. This will get used for early stopping. (Usually small, 0.01 or 0.05.)
Last updated