metadata

language: en
license: apache-2.0
library_name: pytorch
tags:
  - deep-reinforcement-learning
  - reinforcement-learning
  - DI-engine
  - QbertNoFrameskip-v4
benchmark_name: OpenAI/Gym/Atari
task_name: QbertNoFrameskip-v4
pipeline_tag: reinforcement-learning
model-index:
  - name: DQN
    results:
      - task:
          type: reinforcement-learning
          name: reinforcement-learning
        dataset:
          name: OpenAI/Gym/Atari-QbertNoFrameskip-v4
          type: OpenAI/Gym/Atari-QbertNoFrameskip-v4
        metrics:
          - type: mean_reward
            value: 16375.0 +/- 0.0
            name: mean_reward

Play QbertNoFrameskip-v4 with DQN Policy

Model Description

This is a simple DQN implementation to OpenAI/Gym/Atari QbertNoFrameskip-v4 using the DI-engine library and the DI-zoo.

DI-engine is a python library for solving general decision intelligence problems, which is based on implementations of reinforcement learning framework using PyTorch or JAX. This library aims to standardize the reinforcement learning framework across different algorithms, benchmarks, environments, and to support both academic researches and prototype applications. Besides, self-customized training pipelines and applications are supported by reusing different abstraction levels of DI-engine reinforcement learning framework.

Model Usage

Install the Dependencies

(Click for Details)

# install huggingface_ding
git clone https://github.com/opendilab/huggingface_ding.git
pip3 install -e ./huggingface_ding/
# install environment dependencies if needed
pip3 install DI-engine[common_env]

Git Clone from Huggingface and Run the Model

(Click for Details)

# running with trained model
python3 -u run.py

run.py

# [More Information Needed]

Run Model by Using Huggingface_ding

(Click for Details)

# running with trained model
python3 -u run.py

run.py

# [More Information Needed]

Model Training

Train the Model and Push to Huggingface_hub

(Click for Details)

#Training Your Own Agent
python3 -u train.py

train.py

# [More Information Needed]

Configuration

(Click for Details)

exp_config = {
    'env': {
        'manager': {
            'episode_num': float("inf"),
            'max_retry': 1,
            'retry_type': 'reset',
            'auto_reset': True,
            'step_timeout': None,
            'reset_timeout': None,
            'retry_waiting_time': 0.1,
            'cfg_type': 'BaseEnvManagerDict'
        },
        'stop_value': 30000,
        'n_evaluator_episode': 8,
        'env_id': 'QbertNoFrameskip-v4',
        'collector_env_num': 8,
        'evaluator_env_num': 8,
        'fram_stack': 4,
        'env_wrapper': 'atari_default'
    },
    'policy': {
        'model': {
            'encoder_hidden_size_list': [128, 128, 512],
            'obs_shape': [4, 84, 84],
            'action_shape': 6
        },
        'learn': {
            'learner': {
                'train_iterations': 1000000000,
                'dataloader': {
                    'num_workers': 0
                },
                'log_policy': True,
                'hook': {
                    'load_ckpt_before_run': '',
                    'log_show_after_iter': 100,
                    'save_ckpt_after_iter': 10000,
                    'save_ckpt_after_run': True
                },
                'cfg_type': 'BaseLearnerDict'
            },
            'update_per_collect': 10,
            'batch_size': 32,
            'learning_rate': 0.0001,
            'target_update_freq': 500,
            'target_theta': 0.005,
            'ignore_done': False
        },
        'collect': {
            'collector': {},
            'n_sample': 100,
            'unroll_len': 1
        },
        'eval': {
            'evaluator': {
                'eval_freq': 1000,
                'render': {
                    'render_freq': -1,
                    'mode': 'train_iter'
                },
                'figure_path': None,
                'cfg_type': 'InteractionSerialEvaluatorDict',
                'stop_value': 30000,
                'n_episode': 8
            }
        },
        'other': {
            'replay_buffer': {
                'replay_buffer_size': 400000
            },
            'eps': {
                'type': 'exp',
                'start': 1.0,
                'end': 0.05,
                'decay': 1000000
            }
        },
        'on_policy': False,
        'cuda': True,
        'multi_gpu': False,
        'bp_update_sync': True,
        'traj_len_inf': False,
        'type': 'dqn',
        'priority': False,
        'priority_IS_weight': False,
        'discount_factor': 0.99,
        'nstep': 3,
        'cfg_type': 'DQNPolicyDict'
    },
    'exp_name': 'QbertNoFrameskip-v4-DQN',
    'seed': 0,
    'wandb_logger': {
        'gradient_logger': True,
        'video_logger': True,
        'plot_logger': True,
        'action_logger': True,
        'return_logger': False
    }
}

Training Procedure

Weights & Biases (wandb): monitor link

Model Information

Github Repository: repo link
Doc: DI-engine-docs Algorithm link
Configuration: config link
Demo: video
Parameters total size: 55703.03 KB
Last Update Date: 2023-07-23

Environments

Benchmark: OpenAI/Gym/Atari
Task: QbertNoFrameskip-v4
Gym version: 0.25.1
DI-engine version: v0.4.8
PyTorch version: 2.0.1+cu117
Doc: DI-engine-docs Environments link