Set browser variables to corresponding link, page HTML for URL

Returns arr[start] + ... + arr[end] :param start: (int) start position of the reduction (must be >= 0) :param end: (int) end

Wrapper for `receive` handler for performing search action on current page

overrides ai2thor.controller.Controller.step() for smooth navigation and goal_condition updates

Write the sequence of args, with no separators, to the console and output files (if you've configured an output file).

Redirect to the search page with the given session ID

Close the environment and release resources.

Softmax with mask (optional)

Encode an observation

Tell the agent that it's evaluation phase.

Returns min(arr[start], ..., arr[end]) :param start: (int) start position of the reduction (must be >= 0) :param end: (int)

Partially borrowed from Keras # Arguments sequences: list of lists where each element is a sequence maxlen: int, maximum leng

Generate an action by maximum q values.

Execute a tool with given parameters.

Log a value of some diagnostic Call this once for each diagnostic quantity, each iteration If called many times, last value will be used.

Reset agent state for new episode.

Step environment.

returns a dictionary of all targets for the task

Reset internal states

Dummy encode.

exhaustive list of admissible commands

Process predictions into actions and content based on XML-like tags. Does not require tool_manager. Args: predic

Store content to memory.md file. Args: content: Text to store episode: Episode identifier

Dummy decode - return staged format strings for VERL compatibility.

Returns a state representation built from various info sources.

Write all of the diagnostics from the current iteration level: int. (see logger.py docs) If the global logger level is higher than

Fetches memory records at a specific time step across all environments.

Generate responses based on input.

Process response using modular stage processor. Returns (env_action, processed_data).

Tell the agent that it's training phase.

Shape: - y_pred: batch x time x vocab - y_true: batch x time - mask: batch x time