Skip to main content
Ctrl+K
Logo image

Site Navigation

  • Overview
  • Quickstart
  • Examples
  • Changelogs
  • API Reference
  • Developer Guide

Site Navigation

  • Overview
  • Quickstart
  • Examples
  • Changelogs
  • API Reference
  • Developer Guide

Section Navigation

  • Input/Output
    • a2rl.list_sample_datasets
    • a2rl.read_csv_dataset
    • a2rl.sample_dataset_path
    • a2rl.Metadata
    • a2rl.read_metadata
    • a2rl.save_metadata
    • a2rl._metadatadict.MetadataDict
  • Data Structures
    • a2rl.WiDataFrame
      • a2rl.WiDataFrame.add_value
      • a2rl.WiDataFrame.add_value_for_multi_episode_process
      • a2rl.WiDataFrame.to_csv_dataset
      • a2rl.WiDataFrame.trim
      • a2rl.WiDataFrame.actions
      • a2rl.WiDataFrame.rewards
      • a2rl.WiDataFrame.sar
      • a2rl.WiDataFrame.sar_d
      • a2rl.WiDataFrame.sequence
      • a2rl.WiDataFrame.states
    • a2rl.WiSeries
      • a2rl.WiSeries.to_csv_dataset
      • a2rl.WiSeries.actions
      • a2rl.WiSeries.rewards
      • a2rl.WiSeries.sar
      • a2rl.WiSeries.sar_d
      • a2rl.WiSeries.states
    • a2rl.TransitionRecorder
      • a2rl.TransitionRecorder.reset
      • a2rl.TransitionRecorder.start
      • a2rl.TransitionRecorder.step
      • a2rl.TransitionRecorder.stop
  • Tokenizer
    • a2rl.Tokenizer
      • a2rl.Tokenizer.fit
      • a2rl.Tokenizer.fit_transform
      • a2rl.Tokenizer.inverse_transform
      • a2rl.Tokenizer.transform
      • a2rl.Tokenizer.valid_tokens
      • a2rl.Tokenizer.valid_tokens_of_col_idx
      • a2rl.Tokenizer.valid_tokens_of_col_name
    • a2rl.DiscreteTokenizer
      • a2rl.DiscreteTokenizer.check_categorical_columns
      • a2rl.DiscreteTokenizer.check_numerical_columns
      • a2rl.DiscreteTokenizer.fit
      • a2rl.DiscreteTokenizer.fit_transform
      • a2rl.DiscreteTokenizer.inverse_transform
      • a2rl.DiscreteTokenizer.transform
      • a2rl.DiscreteTokenizer.valid_tokens
      • a2rl.DiscreteTokenizer.valid_tokens_of_col_idx
      • a2rl.DiscreteTokenizer.valid_tokens_of_col_name
  • Simulator
    • a2rl.AutoTokenizer
      • a2rl.AutoTokenizer.from_seq_to_dataframe
      • a2rl.AutoTokenizer.gpt_inverse_tokenize
      • a2rl.AutoTokenizer.gpt_tokenize
      • a2rl.AutoTokenizer.col_eligible_index
      • a2rl.AutoTokenizer.gpt_token_to_tokenized_val_map
      • a2rl.AutoTokenizer.gym_action_to_enc
      • a2rl.AutoTokenizer.gym_enc_to_action
      • a2rl.AutoTokenizer.tokenized_val_to_gpt_token_map
    • a2rl.GPTBuilder
      • a2rl.GPTBuilder.config_loader
      • a2rl.GPTBuilder.evaluate
      • a2rl.GPTBuilder.fit
      • a2rl.GPTBuilder.load_model
      • a2rl.GPTBuilder.sample
      • a2rl.GPTBuilder.save_model
      • a2rl.GPTBuilder.model
    • a2rl.Simulator
      • a2rl.Simulator.beam_search_n_steps
      • a2rl.Simulator.get_valid_actions
      • a2rl.Simulator.gpt_sample
      • a2rl.Simulator.gpt_sample_n_steps
      • a2rl.Simulator.lookahead
      • a2rl.Simulator.reset
      • a2rl.Simulator.sample
      • a2rl.Simulator.step
      • a2rl.Simulator.current_context
    • a2rl.SimulatorWrapper
      • a2rl.SimulatorWrapper.action
      • a2rl.SimulatorWrapper.reverse_action
      • a2rl.SimulatorWrapper.gym_action_to_enc
  • Utilities
    • a2rl.utils.action_effective
    • a2rl.utils.action_reward
    • a2rl.utils.backtest
    • a2rl.utils.better_than_random
    • a2rl.utils.conditional_entropy
    • a2rl.utils.data_generator_simple
    • a2rl.utils.entropy
    • a2rl.utils.force_assert
    • a2rl.utils.information_gain
    • a2rl.utils.is_markovian
    • a2rl.utils.markovian_matrix
    • a2rl.utils.normalized_markovian_matrix
    • a2rl.utils.plot_information
    • a2rl.utils.reward_function
    • a2rl.utils.set_seed
    • a2rl.utils.stationary_policy
    • a2rl.utils.tokenize
  • Experimental
    • a2rl.experimental.lightgpt.LightGPTBuilder
      • a2rl.experimental.lightgpt.LightGPTBuilder.config_loader
      • a2rl.experimental.lightgpt.LightGPTBuilder.evaluate
      • a2rl.experimental.lightgpt.LightGPTBuilder.fit
      • a2rl.experimental.lightgpt.LightGPTBuilder.load_model
      • a2rl.experimental.lightgpt.LightGPTBuilder.sample
      • a2rl.experimental.lightgpt.LightGPTBuilder.save_model
      • a2rl.experimental.lightgpt.LightGPTBuilder.model
  • API Reference
  • a2rl.Simulator
  • a2rl.Simulator.step

a2rl.Simulator.step#

Simulator.step(action)[source]#

Placeholder.

Return type:

tuple[ndarray, float, bool, dict]

previous

a2rl.Simulator.sample

next

a2rl.Simulator.current_context
On this page
  • Simulator.step()
Edit on GitHub
Show Source

© Copyright 2022, AWS ProServe.

Created using Sphinx 6.2.1.

Built with the PyData Sphinx Theme 0.13.3.